発表文献

これまでに発表された文献の一覧(2019年10月~)

学術論文誌

  1. Li Li, Hirokazu Kameoka, Shoji Makino, "FastMVAE2: on improving and accelerating the fast variational autoencoder-based source separation algorithm for determined mixtures," IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 31, pp. 96-110, Oct. 14, 2022. [arXiv preprint]
  2. Yi-Chiao Wu, Patrick Lumban Tobing, Kazuki Yasuhara, Noriyuki Matsunaga, Yamato Ohtani, Tomoki Toda, "A cyclical approach to synthetic and natural speech mismatch refinement of neural post-filter for low-cost text-to-speech system," APSIPA Transactions on Signal and Information Processing, Vol. 11, No. 1, e30, pp. 1-32, Sep. 21, 2022. [Open Access]
  3. Wen-Chin Huang, Shu-Wen Yang, Tomoki Hayashi, Tomoki Toda, "A comparative study of self-supervised speech representation based voice conversion," IEEE Journal of Selected Topics in Signal Processing, Vol. 16, No. 6, pp. 1308-1318, July 25, 2022. [arXiv preprint]
  4. 春田 智穂, 小野 順貴, "補聴器応用のためのDNN音声強調の低演算量化の検討," 日本音響学会誌, Vol. 78, No. 5, pp. 227-237, May 1, 2022. [Link]
  5. Kouei Yamaoka, Nobutaka Ono, Shoji Makino, "Time-frequency-bin-wise linear combination of beamformers for distortionless signal enhancement," IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 29, pp. 3461-3475, Nov. 13, 2021. [Open Access]【第38回電気通信普及財団賞 テレコムシステム技術学生賞(受賞者:Kouei Yamaoka)】
  6. Kanato Ishii, Yuma Kinoshita, Yukoh Wakabayashi, Nobutaka Ono, "Real-time pitch visualization with "Blinky" sound-to-light conversion device," Journal of Signal Processing, Vol. 25, No. 6, pp. 213-220, Nov. 1, 2021. [Open Access]
  7. Chihiro Watanabe, Hirokazu Kameoka, "X-DC: explainable deep clustering based on learnable spectrogram templates," Neural Computation, Vol. 33, No. 7, pp. 1853-1885, June 11, 2021. [arXiv preprint]
  8. Yi-Chiao Wu, Tomoki Hayashi, Patrick Lumban Tobing, Kazuhiro Kobayashi, Tomoki Toda, "Quasi-periodic WaveNet: an autoregressive raw waveform generative model with pitch-dependent dilated convolution neural network," IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 29, pp. 1134-1148, Feb. 23, 2021. [Open Access]
  9. Yi-Chiao Wu, Tomoki Hayashi, Takuma Okamoto, Hisashi Kawai, Tomoki Toda, "Quasi-periodic parallel WaveGAN: a non-autoregressive raw waveform generative model with pitch-dependent dilated convolution neural network," IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 29, pp. 792-806, Jan. 14, 2021. [Open Access]
  10. Wen-Chin Huang, Tomoki Hayashi, Yi-Chiao Wu, Hirokazu Kameoka, Tomoki Toda, "Pretraining techniques for sequence-to-sequence voice conversion," IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 29, pp. 745-755, Jan. 5, 2021. [Open Access]【IEEE Signal Processing Society Japan Young Author Best Paper Award(受賞者:Wen-Chin Huang)】
  11. Hirokazu Kameoka, Wen-Chin Huang, Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo, Tomoki Toda, "Many-to-many voice transformer network," IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 29, pp. 656-670, Dec. 24, 2020. [arXiv preprint]
  12. Li Li, Hirokazu Kameoka, Shota Inoue, Shoji Makino, "FastMVAE: a fast optimization algorithm for the multichannel variational autoencoder method," IEEE Access, Vol. 8, pp. 228740-228753, Dec. 1, 2020. [Open Access]
  13. Li Li, Hirokazu Kameoka, Shoji Makino, "Majorization-minimization algorithm for discriminative non-negative matrix factorization," IEEE Access, Vol. 8, pp. 227399-227408, Dec. 18, 2020. [Open Access]
  14. Patrick Lumban Tobing, Yi-Chiao Wu, Tomoki Hayashi, Kazuhiro Kobayashi, Tomoki Toda, "An evaluation of voice conversion with neural network spectral mapping models and WaveNet vocoder," APSIPA Transactions on Signal and Information Processing, Vol. 9, e26, pp. 1-14, Nov. 25, 2020. [Open Access]
  15. Tomohiko Nakamura, Hirokazu Kameoka, "Harmonic-temporal factor decomposition for unsupervised monaural separation of harmonic sounds," IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 29, pp. 68-82, Nov. 16, 2020. [Open Access]
  16. Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, "Nonparallel voice conversion with augmented classifier star generative adversarial networks," IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 28, pp. 2982-2995, Nov. 11, 2020. [arXiv preprint]
  17. Hirokazu Kameoka, Kou Tanaka, Damian Kwasny, Takuhiro Kaneko, Nobukatsu Hojo, "ConvS2S-VC: fully convolutional sequence-to-sequence voice conversion," IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 28, pp. 1849-1863, June 10. 2020. [Open Access]
  18. Yi-Chiao Wu, Patrick Lumban Tobing, Tomoki Hayashi, Kazuhiro Kobayashi, Tomoki Toda, "Non-parallel voice conversion system with WaveNet vocoder and collapsed speech suppression," IEEE Access, Vol. 8, pp. 62094-62106, Mar. 30, 2020. [Open Access]
  19. (Patrick Lumban Tobing, Yi-Chiao Wu, Tomoki Hayashi, Kazuhiro Kobayashi, Tomoki Toda, "Voice conversion with CycleRNN-based spectral mapping and finely-tuned WaveNet vocoder," IEEE Access, Vol. 7, pp. 171114-171125, Nov. 26, 2019. [Open Access])
  20. (Shogo Seki, Hirokazu Kameoka, Li Li, Tomoki Toda, Kazuya Takeda, "Underdetermined source separation based on generalized multichannel variational autoencoder," IEEE Access, Vol. 7, pp. 168104-168115, Nov. 19, 2019. [Open Access])
 

国際会議

  1. Yusuke Yasuda, Tomoki Toda, "Text-to-speech synthesis based on latent variable conversion using diffusion probabilistic model and variational autoencoder," Proc. IEEE ICASSP, 5 pages, June 4, 2023. [arXiv preprint]
  2. Kazuhiro Kobayashi, Tomoki Hayashi, Tomoki Toda, "Low-latency electrolaryngeal speech enhancement based on FastSpeech2-based voice conversion and self-supervised speech representation," Proc. IEEE ICASSP, 5 pages, June 4, 2023. [Link]
  3. Ryuichi Yamamoto, Reo Yoneyama, Tomoki Toda, "NNSVS: a neural network based singing voice synthesis toolkit," Proc. IEEE ICASSP, 5 pages, June 4, 2023. [arXiv preprint]
  4. Reo Yoneyama, Yi-Chiao Wu, Tomoki Toda, "Source-Filter HiFiGAN: fast and pitch controllable high-fidelity neural vocoder", Proc. IEEE ICASSP, 5 pages, June 4, 2023. [arXiv preprint]
  5. Takuya Fujimura, Tomoki Toda, "Analysis of Noisy-target Training for DNN-based speech enhancement," Proc. IEEE ICASSP, 5 pages, June 4, 2023. [arXiv preprint]
  6. Atsushi Miyashita, Tomoki Toda, "Representation of vocal tract length transformation based on group theory," Proc. IEEE ICASSP, 5 pages, June 4, 2023. [Link]
  7. Taishi Nakashima, Rintaro Ikeshita, Nobutaka Ono, Shoko Araki, Tomohiro Nakatani, "Fast online source steering algorithm for tracking single moving source using online independent vector analysis," Proc. IEEE ICASSP, 5 pages, June 4, 2023. [Link]
  8. Taiga Kawamura, Natsuki Ueno, Nobutaka Ono, "Element selection with wide class of optimization criteria using non-convex sparse optimization," Proc. IEEE ICASSP, 5 pages, June 4, 2023. [Link]
  9. Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki, "Wave-U-Net discriminator: fast and lightweight discriminator for generative adversarial network-based speech synthesis," Proc. IEEE ICASSP, 5 pages, June 4, 2023. [arXiv preprint]
  10. Shogo Seki, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, "JSV-VC: Jointly trained speaker verification and voice conversion models," Proc. IEEE ICASSP, 5 pages, June 4, 2023. [Link]
  11. Yoshiki Masuyama, Xuankai Chang, Samuele Cornell, Shinji Watanabe, Nobutaka Ono, "End-to-end integration of speech recognition, dereverberation, beamforming, and self-supervised learning representation," Proc. IEEE SLT, pp. 260-265, Jan. 9, 2023. [arXiv preprint]【Best Student Paper Award(受賞者:Yoshiki Masuyama)】
  12. Ding Ma, Lester Phillip Violeta, Kazuhiro Kobayashi, Tomoki Toda, "Two-stage training method for Japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion," Proc. IEEE SLT, pp. 949-954, Jan. 9, 2023. [arXiv preprint]
  13. Satoshi Motoyama, Natsuki Ueno, Yuma Kinoshita, Nobutaka Ono, "Compressed sensing of sparse spectrum using distributed sound-to-light conversion device Blinkies," Proc. APSIPA ASC, pp. 12-16, Nov. 7, 2022. [Open Access]
  14. Yuka Hashizume, Li Li, Tomoki Toda, "Music similarity calculation of individual instrumental sounds using metric learning," Proc. APSIPA ASC, pp. 33-38, Nov. 7, 2022. [Open Access]
  15. Jingyi Feng, Tomohiro Yoshikawa, Tomoki Toda, "Interpretable control for emotional text-to-speech system toward development of sympathetic educational-support robots," Proc. APSIPA ASC, pp. 342-346, Nov. 7, 2022. [Open Access]
  16. Rui Wang, Li Li, Tomoki Toda, "Direction-aware target speaker extraction with a dual-channel system based on conditional variational autoencoders under underdetermined conditions," Proc. APSIPA ASC, pp. 347-353, Nov. 7, 2022. [Open Access]
  17. Shuhei Yamaji, Taishi Nakashima, Nobutaka Ono, Li Li, Hirokazu Kameoka, "Encoder re-training with mixture signals on FastMVAE method," Proc. APSIPA ASC, pp. 705-709, Nov. 7, 2022. [Open Access]
  18. Kosuke Nishida, Natsuki Ueno, Yuma Kinoshita, Nobutaka Ono, "Estimation of transfer coefficients and signals of sound-to-light conversion device Blinky under saturation," Proc. APSIPA ASC, pp. 718-723, Nov. 7, 2022. [Open Access]
  19. Taishi Nakashima, Nobutaka Ono, "Inverse-free online independent vector analysis with flexible iterative source steering," Proc. APSIPA ASC, pp. 750-754, Nov. 7, 2022. [Open Access]
  20. Yui Kuriki, Taishi Nakashima, Kouei Yamaoka, Natsuki Ueno, Yukoh Wakabayashi, Nobutaka Ono, Ryo Sato, "Efficient low-latency convolution with uniform filter partition and its evaluation on real-time blind source separation," Proc. APSIPA ASC, pp. 766-770, Nov. 7, 2022. [Open Access]
  21. Kenta Yamada, Yoshiki Masuyama, Yukoh Wakabayashi, Nobutaka Ono, "Simultaneous frequency estimation for three or more sinusoids based on sinusoidal constraint differential equation," Proc. APSIPA ASC, pp. 976-979, Nov. 7, 2022. [Open Access]
  22. Kohei Suzuki, Shoki Sakamoto, Tadahiro Taniguchi, Hirokazu Kameoka, "Speak like a dog: human to non-human creature voice conversion," Proc. APSIPA ASC, pp. 1385-1390, Nov. 7, 2022. [Open Access]
  23. Shaowen Chen, Tomoki Toda, "Sequence-wise optimization for quasi-harmonic speech waveform modeling," Proc. APSIPA ASC, pp. 1658-1663, Nov. 7, 2022. [Open Access]
  24. Chao Xie, Tomoki Toda, "Noisy-to-noisy voice conversion with pre-training strategy," Proc. ICA, ABS-0801, 5 pages, Oct. 2022 (Invited in structured session "A15-06: Voice conversion").
  25. Hirokazu Kameoka, Takuhiro Kaneko, Shogo Seki, Kou Tanaka, "CAUSE: Crossmodal action unit sequence estimation from speech with application to facial animation synthesis," Proc. INTERSPEECH, pp. 506-510, Sep. 18, 2022. [Open Access]
  26. Yoshiki Masuyama, Kouei Yamaoka, Nobutaka Ono, "Joint optimization of sampling rate offsets based on entire signal relationship among distributed microphones," Proc. INTERSPEECH, pp. 704-708, Sep. 18, 2022. [Open Access]
  27. Reo Yoneyama, Yi-Chiao Wu, Tomoki Toda, "Unified source-filter GAN with harmonic-plus-noise source excitation generation," Proc. INTERSPEECH, pp. 848-852, Sep. 18, 2022. [Open Access]
  28. Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki, "MISRNet: Lightweight neural vocoder using multi-input single shared residual blocks," Proc. INTERSPEECH, pp. 1631-1635, Sep. 18, 2022. [Open Access]
  29. Wen-Chin Huang, Erica Cooper, Yu Tsao, Hsin-Min Wang, Tomoki Toda, Junichi Yamagishi, "The VoiceMOS Challenge 2022," Proc. INTERSPEECH, pp. 4536-4540, Sep. 18, 2022. [Open Access]
  30. Yeonjong Choi, Chao Xie, Tomoki Toda, "An evaluation of three-stage voice conversion framework for noisy and reverberant conditions," Proc. INTERSPEECH, pp. 4910-4914, Sep. 18, 2022. [Open Access]
  31. Natsuki Ueno, Hirokazu Kameoka, "Multiple sound source localization based on stochastic modeling of spatial gradient spectra," Proc. EUSIPCO, pp. 31-35, Aug. 29, 2022. [Open Access]
  32. Sehun Kim, Tomoki Hayashi, Tomoki Toda, "Note-level automatic guitar transcription using attention mechanism," Proc. EUSIPCO, pp. 229-233, Aug. 29, 2022. [Open Access]
  33. Shuming Luan, Yukoh Wakabayashi, Tomoki Toda, "Modified sound field interpolation method for rotation-robust beamforming with unequally spaced circular microphone array," Proc. EUSIPCO, pp. 344-348, Aug. 29, 2022. [Open Access]
  34. Shogo Seki, Hirokazu Kameoka, Li Li, "Investigation and comparison of optimization methods for variational autoencoder-based underdetermined multichannel source separation," Proc. IEEE ICASSP, pp. 511-515, May 23, 2022. [Link]
  35. Li Li, Hirokazu Kameoka, Shogo Seki, "HBP: An efficient block permutation solver using Hungarian algorithm and spectrogram inpainting for multichannel audio source separation," Proc. IEEE ICASSP, pp. 516-520, May 23, 2022. [Link]
  36. Hirokazu Kameoka, Shogo Seki, Li Li, Chihiro Watanabe, "AttentionPIT: Soft permutation invariant training for audio source separation with attention mechanism," Proc. IEEE ICASSP, pp. 706-710, May 23, 2022. [Link]
  37. Wen-Chin Huang, Erica Cooper, Junichi Yamagishi, Tomoki Toda, "LDNet: unified listener dependent modeling in MOS prediction for synthetic speech," Proc. IEEE ICASSP, pp. 896-900, May 23, 2022. [arXiv preprint]
  38. Natsuki Ueno, Nobutaka Ono, "Instantaneous linear dimensionality reduction of multichannel time-series signal for array signal processing," Proc. IEEE ICASSP, pp. 931-935, May 23, 2022. [Link]
  39. Takuhiro Kaneko, Kou Tanaka, Hirokazu Kameoka, Shogo Seki, "iSTFTNet: Fast and lightweight mel-spectrogram vocoder incorporating inverse short-time Fourier transform," Proc. IEEE ICASSP, pp. 6207-6211, May 23, 2022. [arXiv preprint]
  40. Wen-Chin Huang, Shu-Wen Yang, Tomoki Hayashi, Hung-Yi Lee, Shinji Watanabe, Tomoki Toda, "S3PRL-VC: open-source voice conversion framework with self-supervised speech representations," Proc. IEEE ICASSP, pp. 6552-6556, May 23, 2022. [arXiv preprint]
  41. Wen-Chin Huang, Bence Mark Halpern, Lester Phillip Violeta, Odette Scharenborg, Tomoki Toda, "Towards identity preserving normal to dysarthric voice conversion," Proc. IEEE ICASSP, pp. 6672-6676, May 23, 2022. [arXiv preprint]
  42. Chao Xie, Yi-Chiao Wu, Patrick Lumban Tobing, Wen-Chin Huang, Tomoki Toda, "Direct noisy speech modeling for noisy-to-noisy voice conversion," Proc. IEEE ICASSP, pp. 6787-6791, May 23, 2022. [arXiv preprint]
  43. Tomoki Hayashi, Kazuhiro Kobayashi, Tomoki Toda, "An investigation of streaming non-autoregressive sequence-to-sequence voice conversion," Proc. IEEE ICASSP, pp. 6802-6806, May 23, 2022. [Link]
  44. Erica Cooper, Wen-Chin Huang, Tomoki Toda, Junichi Yamagishi, "Generalization ability of MOS prediction networks," Proc. IEEE ICASSP, pp. 8442-8446, May 23, 2022. [arXiv preprint]
  45. Koudai Mogi, Taishi Nakashima, Kouei Yamaoka, Yukoh Wakabayashi, Nobutaka Ono, "Source selection using multiple directions of arrival estimation based on blind source separation," Proc. NCSP, pp. 253-256, Mar. 2022.【NCSP'22 Best Student Paper Award(受賞者:Koudai Mogi)】
  46. Wen-Chin Huang, Shu-Wen Yang, Tomoki Hayashi, Hung-Yi Lee, Shinji Watanabe, Tomoki Toda, "S3PRL-VC: open-source voice conversion framework with self-supervised speech representations," Proc. AAAI-22 Workshop, W35: Self-Supervised Learning for Audio and Speech Processing, 5 pages, Feb. 2022. [Open Access]
  47. Zhaopeng Qian, Haijun Niu, Li Wang, Kazuhiro Kobayashi, Shaochuan Zhang, Tomoki Toda, "Mandarin electro-laryngeal speech enhancement based on statistical voice conversion and manual tone control," Proc. APSIPA ASC, pp. 546-552, Dec. 14, 2021. [Open Access]
  48. Yoshiki Masuyama, Kouei Yamaoka, Yuma Kinoshita, Nobutaka Ono, "Causal distortionless response beamforming by alternating direction method of multipliers," Proc. APSIPA ASC, pp. 585-590, Dec. 14, 2021. [Open Access]
  49. Chao Xie, Yi-Chiao Wu, Patrick Lumban Tobing, Wen-Chin Huang, Tomoki Toda, "Noisy-to-noisy voice conversion framework with denoising model," Proc. APSIPA ASC, pp. 814-820, Dec. 14, 2021. [Open Access]
  50. Ding Ma, Wen-Chin Huang, Tomoki Toda, "Investigation of text-to-speech-based synthetic parallel data for sequence-to-sequence non-parallel voice conversion," Proc. APSIPA ASC, pp. 870-877, Dec. 14, 2021. [Open Access]【APSIPA ASC 2021 The Best Paper Award】
  51. Guansan Lian, Yukoh Wakabayashi, Taishi Nakashima, Nobutaka Ono, "Self-rotation angle estimation of circular microphone array based on sound field interpolation," Proc. APSIPA ASC, pp. 1016-1020, Dec. 14, 2021. [Open Access]
  52. Yuma Kinoshita, Nobutaka Ono, "Analysis on roles of DNNs in end-to-end acoustic scene analysis framework with distributed sound-to-light conversion devices," Proc. APSIPA ASC, pp. 1167-1172, Dec. 14, 2021. [Open Access]【APSIPA ASC 2021 The Best Paper Award】
  53. Chiho Haruta, Nobutaka Ono, Yuma Kinoshita, "Framewise finite impulse response filtering based on time-frequency mask for low-latency speech enhancement," Proc. APSIPA ASC, pp. 1215-1220, Dec. 14, 2021. [Open Access]
  54. Yi-Syuan Liou, Wen-Chin Huang, Ming-Chi Yen, Shu-Wei Tsai, Yu-Huai Peng, Tomoki Toda, Yu Tsao, Hsin-Min Wang, "Time alignment using lip images for frame-based electrolaryngeal voice conversion," Proc. APSIPA ASC, pp. 1234-1238, Dec. 14, 2021. [Open Access]
  55. Wen-Chin Huang, Tomoki Hayashi, X. Li, Shinji Watanabe, Tomoki Toda, "On prosody modeling for ASR+TTS based voice conversion," Proc. IEEE ASRU, pp. 642-649, Dec. 13, 2021. [arXiv preprint]
  56. Ming-Chi Yen, Wen-Chin Huang, Kazuhiro Kobayashi, Yu-Huai Peng, Shu-Wei Tsai, Yu Tsao, Tomoki Toda, Jyh-Shing Roger Jang, Hsin-Min Wang, "Mandarin electrolaryngeal speech voice conversion with sequence-to-sequence modeling," Proc. IEEE ASRU, pp. 650-657, Dec. 13, 2021. [Link]
  57. Shogo Seki, Haruka Taga, Tomoki Toda, "Singing fundamental frequency contour generation using generalized command response model and score-conditional variational autoencoder," Proc. IEEE MLSP, 6 pages, Oct. 25, 2021. [Link]
  58. Wen-Chin Huang, Kazuhiro Kobayashi, Yu-Huai Peng, Ching-Feng Liu, Yu Tsao, Hsin-Min Wang, Tomoki Toda, "A preliminary study of a two-stage paradigm for preserving speaker identity in dysarthric voice conversion," Proc. INTERSPEECH, pp. 1329-1333, Aug. 30, 2021. [Open Access]
  59. Shoki Sakamoto, Akira Taniguchi, Tadahiro Taniguchi, Hirokazu Kameoka, "StarGAN-VC+ASR: StarGAN-based non-parallel voice conversion regularized by automatic speech recognition," Proc. INTERSPEECH, pp. 1359-1363, Aug. 30, 2021. [Open Access]
  60. Reo Yoneyama, Yi-Chiao Wu, Tomoki Toda, "Unified source-filter GAN: unified source-filter network based on factorization of quasi-periodic parallel WaveGAN," Proc. INTERSPEECH, pp. 2187-2191, Aug. 30, 2021. [Open Access]
  61. Patrick Lumban Tobing, Tomoki Toda, "High-fidelity and low-latency universal neural vocoder based on multiband WaveRNN with data-driven linear prediction for discrete waveform modeling," Proc. INTERSPEECH, pp. 2217-2221, Aug. 30, 2021. [Open Access]
  62. Yi-Chiao Wu, Cheng-Hung Hu, Hung-Shin Lee, Yu-Huai Peng, Wen-Chin Huang, Yu Tsao, Hsin-Min Wang, Tomoki Toda, "Relational data selection for data augmentation of speaker-dependent multi-band MelGAN vocoder," Proc. INTERSPEECH, pp. 3630-3634, Aug. 30, 2021. [Open Access]
  63. Patrick Lumban Tobing, Tomoki Toda, "Low-latency real-time non-parallel voice conversion based on cyclic variational autoencoder and multiband WaveRNN with data-driven linear prediction," Proc. SSW, pp. 142-147, Aug. 26, 2021. [Open Access]
  64. Yuma Kinoshita, Nobutaka Ono, "End-to-end training for acoustic scene analysis with distributed sound-to-light conversion devices," Proc. EUSIPCO, pp. 1010-1014, Aug. 23, 2021. [Open Access]
  65. Chiho Haruta, Nobutaka Ono, "A low-computational DNN-based speech enhancement for hearing aids based on element selection," Proc. EUSIPCO, pp. 1025-1029, Aug. 23, 2021. [Open Access]
  66. Shota Inoue, Hirokazu Kameoka, Li Li, Shoji Makino, "SepNet: a deep separation matrix prediction network for multichannel audio source separation," Proc. IEEE ICASSP, pp. 191-195, June 6, 2021. [Link]
  67. Yukoh Wakabayashi, Kouei Yamaoka, Nobutaka Ono, "Rotation-robust beamforming based on sound field interpolation with regularly circular microphone array," Proc. IEEE ICASSP, pp. 771-775, June 6, 2021. [Link]
  68. Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo, "MaskCycleGAN-VC: learning non-parallel voice conversion with filling in frames," Proc. IEEE ICASSP, pp. 5904-5908, June 6, 2021. [arXiv preprint]
  69. Kazuhiro Kobayashi, Wen-Chin Huang, Yi-Chiao Wu, Patrick Lumban Tobing, Tomoki Hayashi, Tomoki Toda, "Crank: an open-source software for nonparallel voice conversion based on vector-quantized variational autoencoder," Proc. IEEE ICASSP, pp. 5934-5938, June 6, 2021. [arXiv preprint]
  70. Wen-Chin Huang, Yi-Chiao Wu, Tomoki Hayashi, Tomoki Toda, "Any-to-one sequence-to-sequence voice conversion using self-supervised discrete speech representations," Proc. IEEE ICASSP, pp. 5944-5948, June 6, 2021. [arXiv preprint]
  71. Tomoki Hayashi, Wen-Chin Huang, Kazuhiro Kobayashi, Tomoki Toda, "Non-autoregressive sequence-to-sequence voice conversion," Proc. IEEE ICASSP, pp. 7068-7072, June 6, 2021. [arXiv preprint]
  72. Kanato Ishii, Yuma Kinoshita, Yukoh Wakabayashi, Nobutaka Ono, "Real-time pitch visualization using sound-light conversion device Blinky," Proc. NCSP, pp. 101-104, Mar. 1, 2021.
  73. Naoya Murashima, Hirokazu Kameoka, Li Li, Shogo Seki, Shoji Makino, "Single-channel muti-speaker separation via discriminative training of variational autoencoder spectrogram model," Proc. NCSP, pp. 149-152, Mar. 1, 2021.【NCSP'21 Student Paper Award(受賞者:Naoya Murashima)】
  74. Taishi Nakashima, Robin Scheibler, Yukoh Wakabayashi, Nobutaka Ono, "Faster independent low-rank matrix analysis with pairwise updates of demixing vectors," Proc. EUSIPCO, pp. 301-305, Jan. 18, 2021. [Open Access]
  75. Kazuhiro Kobayashi, Tomoki Toda, "Implementation of low-latency electrolaryngeal speech enhancement based on multi-task CLDNN," Proc. EUSIPCO, pp. 396-400, Jan. 18, 2021. [Open Access]
  76. Moe Takada, Shogo Seki, Patrick Lumban Tobing, Tomoki Toda, "Semi-supervised enhancement and suppression of self-produced speech using correspondence between air- and body-conducted signals," Proc. EUSIPCO, pp. 456-460, Jan. 18, 2021. [Open Access]
  77. Daiki Horiike, Robin Scheibler, Yuma Kinoshita, Yukoh Wakabayashi, Nobutaka Ono, "Energy-based multiple source localization with Blinkies," Proc. APSIPA ASC, pp. 443-448, Dec. 7, 2020. [Open Access]
  78. Hikaru Nakatani, Patrick Lumban Tobing, Kazuya Takeda, Tomoki Toda, "Cross-lingual voice conversion with cyclic variational auto-encoder and a WaveNet vocoder," Proc. APSIPA ASC, pp. 520-526, Dec. 7, 2020. [Open Access]
  79. Mohammad Eshghi, Kazuhiro Kobayashi, Kou Tanaka, Hirokazu Kameoka, Tomoki Toda, "Phoneme embeddings on predicting fundamental frequency pattern for electrolaryngeal speech," Proc. APSIPA ASC, pp. 572-577, Dec. 7, 2020. [Open Access]
  80. Taishi Nakashima, Robin Scheibler, Yukoh Wakabayashi, Nobutaka Ono, "Performance evaluation of independent low-rank matrix analysis for short signals," Proc. Forum Acusticum, pp. 837-840, Dec. 7, 2020. [Open Access]
  81. Zhao Yi, Wen-Chin Huang, Xiaohai Tian, Junichi Yamagishi, Rohan Kumar Das, Tomi Kinnunen, Zhenhua Ling, Tomoki Toda, "Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion," Proc. Joint workshop for the Blizzard Challenge and Voice Conversion Challenge 2020, pp. 80-98, Oct. 30, 2020. [Open Access]
  82. Rohan Kumar Das, Tomi Kinnunen, Wen-Chin Huang, Zhenhua Ling, Junichi Yamagishi, Zhao Yi, Xiaohai Tian, Tomoki Toda, "Predictions of subjective ratings and spoofing assessments of Voice Conversion Challenge 2020 submissions," Proc. Joint workshop for the Blizzard Challenge and Voice Conversion Challenge 2020, pp. 99-120, Oct. 30, 2020. [Open Access]
  83. Patrick Lumban Tobing, Yi-Chiao Wu, Tomoki Toda, "Baseline system of Voice Conversion Challenge 2020 with cyclic variational autoencoder and parallel WaveGAN," Proc. Joint workshop for the Blizzard Challenge and Voice Conversion Challenge 2020, pp. 155-159, Oct. 30, 2020. [Open Access]
  84. Wen-Chin Huang, Tomoki Hayashi, Shinji Watanabe, Tomoki Toda, "The sequence-to-sequence baseline for the Voice Conversion Challenge 2020: cascading ASR and TTS," Proc. Joint workshop for the Blizzard Challenge and Voice Conversion Challenge 2020, pp. 160-164, Oct. 30, 2020. [Open Access]
  85. Wen-Chin Huang, Patrick Lumban Tobing, Yi-Chiao Wu, Kazuhiro Kobayashi, Tomoki Toda, "The NU voice conversion system for the Voice Conversion Challenge 2020: on the effectiveness of sequence-to-sequence models and autoregressive neural vocoders," Proc. Joint workshop for the Blizzard Challenge and Voice Conversion Challenge 2020, pp. 165-169, Oct. 30, 2020. [Open Access]
  86. Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo, "CycleGAN-VC3: examining and improving CycleGAN-VCs for mel-spectrogram conversion," Proc. INTERSPEECH, pp. 2017-2021, Oct. 25, 2020. [Open Access]
  87. Yi-Chiao Wu, Tomoki Hayashi, Takuma Okamoto, Hisashi Kawai, Tomoki Toda, "Quasi-periodic parallel WaveGAN vocoder: a non-autoregressive pitch-dependent dilated convolution model for parametric speech generation," Proc. INTERSPEECH, pp. 3535-3539, Full virtual, Oct. 25, 2020. [Open Access]
  88. Yi-Chiao Wu, Patrick Lumban Tobing, Kazuki Yasuhara, Noriyuki Matsunaga, Yamato Ohtani, Tomoki Toda, "A cyclical post-filtering approach to mismatch refinement of neural vocoder for text-to-speech systems," Proc. INTERSPEECH, pp. 3540-3544, Full virtual, Oct. 25, 2020. [Open Access]
  89. Shogo Seki, Moe Takada, Tomoki Toda, "Semi-supervised self-produced speech enhancement and suppression based on joint source modeling of air- and body-conducted signals using variational autoencoder," Proc. INTERSPEECH, pp. 4039-4043, Oct. 25, 2020. [Open Access]
  90. Shu Hikosaka, Shogo Seki, Tomoki Hayashi, Kazuhiro Kobayashi, Kazuya Takeda, Hideki Banno, Tomoki Toda, "Intelligibility enhancement based on speech waveform modification using hearing impairment simulator," Proc. INTERSPEECH, pp. 4059-4063, Oct. 25, 2020. [Open Access]
  91. Wen-Chin Huang, Tomoki Hayashi, Yi-Chiao Wu, Hirokazu Kameoka, Tomoki Toda, "Voice transformer network: sequence-to-sequence voice conversion using transformer with text-to-speech pretraining," Proc. INTERSPEECH, pp. 4676-4680, Full virtual, Oct. 25, 2020. [Open Access]
  92. Patrick Lumban Tobing, Tomoki Hayashi, Yi-Chiao Wu, Kazuhiro Kobayashi, Tomoki Toda, "Cyclic spectral modeling for unsupervised unit discovery into voice conversion with excitation and waveform modeling," Proc. INTERSPEECH, pp. 4861-4865, Oct. 25, 2020. [Open Access]
  93. Li Li, Hirokazu Kameoka, Shoji Makino, "Determined audio source separation with multichannel star generative adversarial network," Proc. IEEE MLSP, 6 pages, Sep. 21, 2020. [Link]
  94. Robin Scheibler, Nobutaka Ono, "Fast and stable blind source separation with rank-1 updates," Proc. IEEE ICASSP, pp. 236-240, May 4. 2020. [Link]
  95. Robin Scheibler, Nobutaka Ono, "Fast independent vector extraction by iterative SINR maximization," Proc. IEEE ICASSP, pp. 601-605, May 4. 2020. [arXiv preprint]
  96. Patrick Lumban Tobing, Yi-Chiao Wu, Tomoki Hayashi, Kazuhiro Kobayashi, Tomoki Toda, "Efficient shallow WaveNet vocoder using multiple samples output based on Laplacian distribution and linear prediction," IEEE ICASSP, pp. 7204-7208, May 4. 2020. [Link]
 

招待講演

  1. 戸田 智基, "音声情報処理の最先端から見える未来," 第64回日本神経学会学術大会 シンポジウム「脳神経内科領域でのAIの未来:基礎研究から臨床応用まで」, S-15-2, 2023年6月1日.
  2. 戸田 智基, "深層生成モデルに基づく音声合成技術", 第21回情報科学技術フォーラム(FIT2022), イベント企画「深層生成モデル」, 神奈川, 2022年9月13日.
  3. 李 莉, "信号の独立性に基づく多チャンネル音源分離," 電気・電子・情報関係学会 東海支部連合大会, 【OS2】音響学の次世代を担う若手研究者による異分野融合セッション, J6-1, オンライン, 2022年8月30日.
  4. 亀岡 弘和, "コミュニケーション機能拡張のための機械学習基盤とクロスモーダル信号生成," 情報処理学会 音学シンポジウム, オンライン, 2022年6月18日.
  5. Wen-Chin Huang, Erica Cooper, Yu Tsao, Hsin-Min Wang, Tomoki Toda, Junichi Yamagishi, "The VoiceMOS Challenge 2022", 情報処理学会音声言語情報処理研究発表会/電子情報通信学会音声研究会, オンライン, 2022年3月23日.
  6. 戸田 智基, "共創型音メディア機能拡張に向けた取り組み," 電気・電子・情報関係学会 東海支部連合大会, 企画セッション「音メディア情報処理と共創型機能拡張への展開」, オンライン, 2021年9月8日.
  7. 戸田 智基, "発声機能拡張のためのインタラクティブ音声変換," 電気・電子・情報関係学会 東海支部連合大会, 企画セッション「音メディア情報処理と共創型機能拡張への展開」, オンライン, 2021年9月8日.
  8. 小野 順貴, "聴覚機能拡張のための低遅延リアルタイム音源分離とブリンキー," 電気・電子・情報関係学会 東海支部連合大会, 企画セッション「音メディア情報処理と共創型機能拡張への展開」, オンライン, 2021年9月8日.
  9. 亀岡 弘和, "コミュニケーション機能拡張のための機械学習基盤とクロスモーダル処理," 電気・電子・情報関係学会 東海支部連合大会, 企画セッション「音メディア情報処理と共創型機能拡張への展開」, オンライン, 2021年9月8日.
  10. 春田 智穂, "要素選択を用いた次元削減によるDNN音声強調の低演算量化の検討," Tokyo BISH Bash #05, オンライン, 2021年6月23日.
  11. Tomoki Toda, "Interactive voice conversion for augmented speech production", SNL, Online, July 2, 2021.
  12. 戸田 智基, "CREST「共生インタラクション」共創型音メディア機能拡張プロジェクト," 情報処理学会音声言語情報処理研究会, オンライン, 2021年2月18日.
  13. Tomoki Toda, "Recent progress on voice conversion: what is next?", IEEE SLT, Online, Jan. 21, 2021.
  14. Tomoki Toda, "Recent trend of voice conversion research and its possible future direction", Keynote, ROCLING (the 32nd Annual Conference on Computational Linguistics and Speech Processing in Taiwan), Taipei, Taiwan, Sep. 24, 2020.
  15. 戸田 智基, "音声変換技術と音声生成機能拡張への応用," 電子情報通信学会2020年総合大会 ソサイエティ合同企画「情報通信技術と人間相互理解の未来」, 2020年3月18日.(大会中止)
  16. 亀岡弘和, 金子卓弘, 田中宏, 北条伸克, "画像変換/系列変換アプローチを用いた音声変換," 第21回音声言語シンポジウム(SP/SLP 2研究会連立開催研究会), 東京, 2019年12月6日.
  17. Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, "Voice conversion with image-to-image translation and sequence-to-sequence learning approaches," SANE 2019 - Speech and Audio in the Northeast, New York, U.S.A., Oct. 24, 2019.
 

国内研究会・大会講演

  1. 藤村 拓弥, 戸田 智基, "大規模雑音混入音声データを利用したDNN音声強調学習の効果," 日本音響学会2023年春季研究発表会, 1-1P-2, pp. 209-210, 2023年3月15日.
  2. 渡邊 千紘, 亀岡 弘和, "F0 パターンと声質情報を解きほぐす深層音声変換モデルの学習法," 日本音響学会2023年春季研究発表会, 1-3-11, pp. 693-694, 2023年3月15日.
  3. 田中 宏, 亀岡 弘和, 金子 卓弘, 関 翔悟, "ストリーミング処理にむけたSequence-to-sequence音声変換モデルの知識蒸留," 日本音響学会2023年春季研究発表会, 1-3-14, pp. 703-704, 2023年3月15日.
  4. 安田 裕介, 戸田 智基, "合成音声の主観評価結果の統計的解析," 日本音響学会2023年春季研究発表会, 1-3Q-11, pp. 841-844, 2023年3月15日.
  5. 金子 卓弘, 亀岡 弘和, 田中 宏, 関 翔悟, "Wave-U-Net Discriminator:敵対的生成ネットワークに基づく音声合成のための高速で軽量な識別器," 日本音響学会2023年春季研究発表会, 2-3-1, pp. 709-710, 2023年3月16日.
  6. 金子 卓弘, 亀岡 弘和, 田中 宏, 関 翔悟, "MISRNet:多入力単共有残差ブロックを用いた軽量なニューラルボコーダ," 日本音響学会2023年春季研究発表会, 2-3-2, pp. 711-712, 2023年3月16日.
  7. 米山 怜於, Y.-C. Wu, 戸田 智基, "SiFi-GAN:音源フィルタ構造に基づくHiFi-GAN," 日本音響学会2023年春季研究発表会, 2-3-5, pp. 721-722, 2023年3月16日.
  8. 中嶋 大志, 池下 林太郎, 小野 順貴, 荒木 章子, 中谷 智広, "独立ベクトル分析によるオンライン音源分離・追跡のための高速最適化," 日本音響学会2023年春季研究発表会, 3-1-6, pp. 185-188, 2023年3月17日.
  9. 山岡 洸瑛,植野 夏樹,小野 順貴, "多チャネル時間差推定における性能限界の導出," 日本音響学会2023年春季研究発表会, 3-1-12, pp. 201-204, 2023年3月17日.
  10. 宮下 敦志, 戸田 智基, "リー群論に基づく一般化ワーピング," 電子情報通信学会音声研究会, 技術研究報告, Vol. 122, No. 389, SP2022-55, pp. 89-94, 2023年2月28日.
  11. 藤村 拓弥, 戸田 智基, "DNN音声強調におけるNoisy-target Trainingの分析と実応用に向けた調査," 電子情報通信学会応用音響研究会, 技術研究報告, Vol. 122, No. 387, EA2022-112, pp. 221-226, 2023年3月1日.
  12. 河村 泰雅,植野 夏樹,小野 順貴, "スパース最適化を用いた要素選択による次元削減," 信号処理シンポジウム, pp. 118-123, 2022年12月13日.
  13. 本山 智司,植野 夏樹,木下 裕磨,小野 順貴, "音光変換デバイス「ブリンキー」を用いた圧縮センシングに基づくスパースなスペクトルの推定," 信号処理シンポジウム, pp. 314-319, 2022年12月15日.
  14. 升山 義紀, 山岡 洸瑛, 木下 裕磨, 小野 順貴, "因果的MPDRビームフォーマのオンライン化およびタップ長の影響評価," 日本音響学会2022年秋季研究発表会, 1-2-1, 講演論文集, pp. 155-156, 9月14日, 2022.
  15. 中嶋 大志, 若林 佑幸, 小野 順貴, "音場補間を用いた円状マイクロホンアレイの回転に頑健なブラインド音源分離," 日本音響学会2022年秋季研究発表会, 1-Q-23, 講演論文集, pp. 331-332, 9月14日, 2022.
  16. 李 莉, 関 翔悟, 亀岡 弘和, "再帰ニューラルネットワーク型音源モデルに基づ く高速多チャンネル変分自己符号化器法," 日本音響学会2022年秋季研究発表会, 1-Q-24, 講演論文集, pp. 333-334, 9月14日, 2022.
  17. 山地 修平,中嶋 大志,小野 順貴,李 莉,亀岡 弘和, "混合信号による符号化器再学習を用いたFastMVAE法に基づく音源分離," 日本音響学会2022年秋季研究発表会, 1-Q-30, 講演論文集, pp. 355-358, 9月14日, 2022.
  18. 連 冠三, 山岡 洸瑛, 若林 佑幸, 小野 順貴, "補助関数法に基づく円状マイクロホンアレイの自己回転角度推定," 日本音響学会2022年秋季研究発表会, 1-R-29, 講演論文集, pp. 459-460, 9月14日, 2022.
  19. Shaowen Chen, Tomoki Toda, "Sequence-wise parameter extraction of quasi-hamonic model for speech waveform generation," 日本音響学会2022年秋季研究発表会, 1-8-7, 講演論文集, pp. 1129-1130, 9月14日, 2022.
  20. 近藤祐斗, 李 莉, 関 翔悟, 亀岡 弘和, "FastMVAE法におけるブロックパーミュテーションを軽減する音源モデル学習," 日本音響学会2022年秋季研究発表会, 2-2-2, 講演論文集, pp. 179-182, 9月15日, 2022.
  21. Rui Wang, Li Li, Tomoki Toda, "Direction-aware target speaker extraction with conditional variational autoencoders and its sensitivity to direction-of-arrival error," 日本音響学会2022年秋季研究発表会, 2-2-6, 講演論文集, pp. 195-196, 9月15日, 2022.【第25回日本音響学会 学生優秀発表賞(受賞者:Rui Wang)】
  22. 藤村 拓弥, 戸田 智基, "DNN音声強調におけるNoisy-target Trainingの挙動分析," 日本音響学会2022年秋季研究発表会, 2-2-7, 講演論文集, pp. 197-198, 9月15日, 2022.
  23. Yeonjong Choi, Chao Xie, Tomoki Toda, "Three-stage voice conversion framework for noisy and reverberant speech," 日本音響学会2022年秋季研究発表会, 2-8-7, 講演論文集, pp. 1159-1160, 9月15日, 2022.
  24. Ding Ma, Lester Phillip Violeta, Kazuhiro Kobayashi, Tomoki Toda, "Sequence-to-sequence voice conversion training using synthetic parallel data for electrolaryngeal speech enhancement," 日本音響学会2022年秋季研究発表会, 2-8-8, 講演論文集, pp. 1161-1162, 9月15日, 2022.
  25. 安田 裕介, 戸田 智基, "拡散確率モデルとアライメントモデルを用いた潜在特徴系列変換に基づくテキスト音声合成," 日本音響学会2022年秋季研究発表会, 2-Q-37, 講演論文集, pp. 1269-1272, 9月15日, 2022.
  26. 山岡 洸瑛, 中嶋 大志, 小野 順貴, "最小全域木を用いた複数時間差の同時推定," 日本音響学会2022年秋季研究発表会, 3-2-10, 講演論文集, pp. 259-262, 9月16日, 2022.
  27. Jingyi Feng, Tomohiro Yoshikawa, Tomoki Toda, "Interpretable emotional control for text-to-speech system toward development of sympathetic educational-support robots," 日本音響学会2022年秋季研究発表会, 3-8-3, 講演論文集, pp. 1189-1190, 9月16日, 2022.
  28. 宮下 敦志, 戸田 智基, "群論を用いた解析的声道長正規化処理と音声認識への応用," 日本音響学会2022年秋季研究発表会, 3-Q-12, 講演論文集, pp. 1339-1340, 9月16日, 2022.
  29. Chao Xie, Tomoki Toda, "Robustness of noisy-to-noisy voice conversion against variations of noisy condition," 日本音響学会2022年秋季研究発表会, 3-Q-40, 講演論文集, pp. 1417-1418, 9月16日, 2022.
  30. 橋爪 優果, 李 莉, 戸田 智基, "各楽器音源に着目した楽曲間類似度学習の評価," 日本音響学会2022年秋季研究発表会, 3-1-5, 講演論文集, pp. 1517-1518, 9月16日, 2022.
  31. Sehun Kim, Tomoki Hayashi, Tomoki Toda, "Note-level automatic guitar transcription using attention mechanism and multi-task learning," 日本音響学会2022年秋季研究発表会, 3-1-7, 講演論文集, pp. 1521-1522, 9月16日, 2022.
  32. 植野 夏樹, 小野 順貴, "アレー信号処理のための瞬時線形次元削減," 電子情報通信学会信号処理研究会, 技術研究報告, Vol. 122, No. 165, SIP2022-65, pp. 81-85, 2022年8月26日.
  33. 宮下 敦志, 戸田 智基, "群論を用いた声道長変換の表現と解析的正規化処理," 電子情報通信学会音声研究会, 技術研究報告, Vol. 122, No. 81, SP2022-11, pp. 41-46, 6月17日, 2022.【音声研究会学生ポスター賞(受賞者:宮下 敦志)】
  34. 橋爪 優果, 李 莉, 戸田 智基, "各楽器音に着目した楽曲間類似度学習," 情報処理学会音楽情報科学研究発表会, 研究報告, Vol. 2022-MUS-134, No. 46, pp. 1-6, 6月18日, 2022.
  35. 小野 順貴, "ブラインド音源分離における分離行列の一般化ランク1更新," 電子情報通信学会応用音響研究会, 技術研究報告, Vol. 122, No. 20, EA2022-06, pp. 26-29, 5月13日, 2022.
  36. 中嶋 大志, 小野 順貴, "Iterative source steering を用いたオンライン補助関数型独立ベクトル分析に基づくブラインド音源分離," 日本音響学会2022年春季研究発表会, 1-1-9, 講演論文集, pp. 185-188, 3月9日, 2022. 【第24回日本音響学会 学生優秀発表賞(受賞者:中嶋 大志)】
  37. 本山 智司, 石井 奏人, 植野 夏樹, 木下 裕磨, 小野 順貴, "音光変換デバイス「ブリンキー」を用いた振幅スペクトルの圧縮センシング," 日本音響学会2022年春季研究発表会, 1-1P-5, 講演論文集, pp. 317-318, 3月9日, 2022.
  38. 西田 光佑, 石井 奏人, 植野 夏樹, 木下 裕磨, 小野 順貴, "音光変換デバイス「ブリンキー」の光信号飽和時における伝達係数と信号の推定," 日本音響学会2022年春季研究発表会, 1-1P-6, 講演論文集, pp. 319-320, 3月9日, 2022.
  39. 米山 怜於, 呉 宜樵, 戸田 智基, "敵対的学習による統合的ソースフィルタネットワークの改良," 日本音響学会2022年春季研究発表会, 1-3-10, 講演論文集, pp. 907-908, 3月9日, 2022.
  40. 橋爪 優果, 李 莉, 戸田 智基, "各楽器音源に着目した距離学習に基づく楽曲間類似度計算," 日本音響学会2022年春季研究発表会, 2-9-12, 講演論文集, pp. 1207-1208, 3月10日, 2022.
  41. 升山 義紀, 山岡 洸瑛, 小野 順貴, "補助関数法による複数の非同期録音信号のブラインド同期," 日本音響学会2022年春季研究発表会, 3-1-6, 講演論文集, pp. 277-280, 3月11日, 2022.
  42. 山田 健太, 升山 義紀, 若林 佑幸, 小野 順貴, "微分方程式に基づく複数の正弦波の周波数同時推定," 日本音響学会2022年春季研究発表会, 3-1-7, 講演論文集, pp. 281-282, 3月11日, 2022.
  43. 栗城 結衣, 中嶋 大志, 山岡 洸瑛, 若林 佑幸, 植野 夏樹, 小野 順貴, "ブロック処理と重畳加算の二重化による畳み込み演算の低遅延化," 日本音響学会2022年春季研究発表会, 3-1-8, 講演論文集, pp. 283-284, 3月11日, 2022.
  44. 山岡 洸瑛, 中嶋 大志, 若林 佑幸, 小野 順貴, "補助関数法を用いた複数時間差のオンライン推定," 日本音響学会2022年春季研究発表会, 3-1-9, 講演論文集, pp. 285-286, 3月11日, 2022.
  45. 金子 卓弘, 田中 宏, 亀岡 弘和, 関 翔悟, "iSTFTNet:逆短時間フーリエ変換を用いた高速で軽量なメルスペクトログラムボコーダ," 日本音響学会2022年春季研究発表会, 3-3-4, 講演論文集, pp. 977-978, 3月11日, 2022.
  46. Rui Wang, Li Li, Tomoki Toda, "Target speaker extraction based on conditional variational autoencoder and directional information in underdetermined condition", 電子情報通信学会応用音響研究会, 技術研究報告, Vol. 121, No. 383, EA2021-76, pp. 76-81, 3月1日, 2022.
  47. 佐治 拓樹, 小林 和弘, 石黒 祥生, 戸田 智基, 大谷 健登, 西野 隆則, 武田 一哉, "声質の可視化を用いた所望音声検索システムの提案," 情報処理学会音楽情報科学研究発表会, 研究報告, Vol. 2022-MUS-133, No. 6, pp. 1-5, 1月25日, 2022.
  48. 李 莉, 亀岡 弘和, 牧野 昭二, "ChimeraACVAE による高速多チャンネル変分自己符号化器法," 日本音響学会2021年秋季研究発表会, 1-1-6, 講演論文集, pp. 129-132, 9月7日, 2021.【第51回日本音響学会 粟屋潔学術奨励賞(受賞者:李 莉)】
  49. 李 莉, 亀岡 弘和, 関 翔悟, "ハンガリー法と欠損帯域補完に基づく周波数領域ブロックパーミュテーション解決法," 日本音響学会2021年秋季研究発表会, 1-1-7, 講演論文集, pp. 133-136, 9月7日, 2021.
  50. 升山 義紀, 山岡 洸瑛, 木下 裕磨, 小野 順貴, "因果的MPDRビームフォーマの近接分離最適化による設計," 日本音響学会2021年秋季研究発表会, 1-1-9, 講演論文集, pp. 139-142, 9月7日, 2021.
  51. 茂木 倖大, 中嶋 大志, 若林 佑幸, 小野 順貴, "ブラインド音源分離に基づく複数音源方向推定を用いた分離音源選択の検討," 日本音響学会2021年秋季研究発表会, 1-1-13, 講演論文集, pp. 153-154, 9月7日, 2021.
  52. 山岡 洸瑛, 小野 順貴, "時間周波数線形結合ビームフォーマの空間フィルタ数に対する音源強調性能の評価," 日本音響学会2021年秋季研究発表会, 2-1-3, 講演論文集, pp. 207-208, 9月8日, 2021.
  53. 春田 智穂, 小野 順貴, "要素選択による低演算量化を用いたDNNマスク推定に基づく音声強調処理," 日本音響学会2021年秋季研究発表会, 2-1-4, 講演論文集, pp. 209-210, 9月8日, 2021.
  54. 若林 佑幸, 山岡 洸瑛, 小野 順貴, "円状マイクロホンアレイを利用した音場補間によるステアリングベクトル補間への応用," 日本音響学会2021年秋季研究発表会, 2-1P-6, 講演論文集, pp. 293-294, 9月8日, 2021.
  55. 山地 修平, 中嶋 大志, 若林 佑幸, 小野 順貴, "ハンガリー法を用いたパーミュテーション解法に基づくブラインド音源分離," 日本音響学会2021年秋季研究発表会, 2-1P-10, 講演論文集, pp. 305-306, 9月8日, 2021.
  56. 米山 怜於, Yi-Chiao Wu, 戸田 智基, "敵対的学習による統合型ソースフィルタネットワーク," 日本音響学会2021年秋季研究発表会, 2-3-2, 講演論文集, pp. 905-906, 9月8日, 2021.【第23回日本音響学会 学生優秀発表賞(受賞者:米山 怜於)】
  57. 大川 舜平, 石黒 祥生, 大谷 健登, 西野 隆典, 小林 和弘, 戸田 智基, 武田 一哉, "電気式人工喉頭を用いた歌唱システムにおける自然な身体動作を利用した歌唱表現付与の提案," 情報処理学会シンポジウム インタラクション2021, pp. 261-266, 3月11日, 2021.
  58. 木下 裕磨,小野 順貴, "音光変換デバイス「ブリンキー」の信号伝搬過程を考慮したEnd-to-End音響シーン分析," 日本音響学会2021年春季研究発表会, 1-1-23, 講演論文集, pp. 191-192, 3月10日, 2021.
  59. 金子 卓弘, 亀岡 弘和, 田中 宏, 北条 伸克, "MaskCycleGAN-VC: フレーム補間との同時学習による高品質ノンパラレル声質変換," 日本音響学会2021年春季研究発表会, 1-2-2, 講演論文集, pp. 779-782, 3月10日, 2021.
  60. 中谷 輝, Patrick Lumban Tobing, 武田 一哉 戸田 智基, "CycleVAEを用いた声質変換におけるWaveNetボコーダのファインチュー ニング法の調査," 日本音響学会2021年春季研究発表会, 1-2-4, 講演論文集, pp. 787-790, 3月10日, 2021.
  61. 大竹 徹郎, 関 翔悟, 戸田 智基, "マルチタスク学習を用いたU-Netに基づく楽曲音源分離に関する調査," 日本音響学会2021年春季研究発表会, 1-9-6, 講演論文集, pp. 1121-1122, 3月10日, 2021.
  62. 関 翔悟, 多賀 遥香, 武田 一哉, 戸田 智基, "音高情報条件つき変分自己符号化器を用いたF0歌唱パターン生成," 日本音響学会2021年春季研究発表会, 1-2Q-6, 講演論文集, pp. 1017-1018, 3月10日, 2021.
  63. 村島 允也, 亀岡 弘和, 李 莉, 関 翔悟, 牧野 昭二, "識別的変分自己符号化器学習による特定話者モノラル音声分離," 日本音響学会2021年春季研究発表会, 2-1-1, 講演論文集, pp. 205-208, 3月11日, 2021.
  64. 井上 翔太, 亀岡 弘和, 李 莉, 牧野 昭二, "SepNet: 高速多チャンネル音源分離のための分離行列予測ネットワーク," 日本音響学会2021年春季研究発表会, 2-1-5, 講演論文集, pp. 221-224, 3月11日, 2021.
  65. 春田 智穂,小野 順貴, "要素選択による次元削減を用いたDNN音声強調処理の低演算量化," 日本音響学会2021年春季研究発表会, 2-1-7, 講演論文集, pp. 229-232, 3月11日, 2021.【第22回日本音響学会 学生優秀発表賞(受賞者:春田 智穂)】
  66. 若林 佑幸,小野 順貴, "音場補間を用いた円状マイクロホンアレイの回転に頑健なビームフォーミング," 日本音響学会2021年春季研究発表会, 2-1-8, 講演論文集, pp. 233-234, 3月11日, 2021.
  67. 安原 和輝, Yi-Chiao Wu, Patrick Lumban Tobing, 松永 悟行, 大谷 大和, 戸田 智基, "テキスト音声合成のためのポストフィルタ用WaveNetボコーダの学習条件に関する評価," 日本音響学会2021年春季研究発表会, 2-2-11, 講演論文集, pp. 865-866, 3月11日, 2021.
  68. 山岡 洸瑛,小野 順貴, "補助関数法に基づく複数のチャネル間時間差の同時推定," 日本音響学会2021年春季研究発表会, 2-1Q-2, 講演論文集, pp. 371-374, 3月11日, 2021.
  69. 佐藤 直哉,若林 佑幸,木下 裕磨,小野 順貴, "直交検波を用いた音光変換デバイス「ブリンキー」のLED位置推定," 日本音響学会2021年春季研究発表会, 2-1Q-6, 講演論文集, pp. 381-382, 3月11日, 2021.
  70. 岩本 基裕,木下 裕磨,若林 佑幸,小野 順貴, "音光変換デバイス「ブリンキー」を用いた音響信号処理のための信号伝搬シミュレータ," 日本音響学会2021年春季研究発表会, 2-1Q-7, 講演論文集, pp. 383-384, 3月11日, 2021.
  71. 連 冠三,中嶋 大志,若林 佑幸,小野 順貴, "音場補間に基づく円状マイクロフォンアレイの自己回転角度推定," 日本音響学会2021年春季研究発表会, 2-1Q-12, 講演論文集, pp. 397-398, 3月11日, 2021.
  72. 米山 怜於, Yi-Chiao Wu, 戸田 智基, "統合型ソースフィルタネットワークによるニューラルボコーダ," 電子情報通信学会音声研究会, 技術研究報告, Vol. 120, No. 399, SP2020-34, pp. 57-62, 3月3日, 2021.
  73. 畔栁 伊吹, 林 知樹, 武田 一哉, 戸田 智基, "特徴量空間のクラス重心を考慮した二値分類モデルによる異常音検知," 電子情報通信学会応用音響研究会 技術研究報告, Vol. 120, No. 397, EA2020-79, pp. 114-121, 3月4日, 2021.
  74. 山岡 洸瑛,小野 順貴, "連続値マスクを用いた複数MVDRビームフォーマの組み合わせによる劣決定音声強調," 日本音響学会2020年秋季研究発表会, 1-1-5, 講演論文集, pp. 123-126, 9月9日, 2020.
  75. 中谷 輝, Patrick Lumban Tobing, 武田 一哉, 戸田 智基, "CycleVAEとWaveNetボコーダを用いたクロスリンガル声質変換," 日本音響学会2020年秋季研究発表会, 1-2-12, 講演論文集, pp. 719-720, 9月9日, 2020.
  76. 多賀 遥香, 関 翔悟, 李 莉, 武田 一哉, 戸田 智基, "一般化指令応答モデルを用いた変分自己符号化器に基づく歌唱F0パターンの生成," 日本音響学会2020年秋季研究発表会, 1-2-16, 講演論文集, pp. 731-732, 9月9日, 2020.
  77. 若林 佑幸, 小野 順貴, "回転移動に頑健なアレイ信号処理のための音場の補間に関する一検討," 日本音響学会2020年秋季研究発表会, 2-1-9, 講演論文集, pp. 187-188, 9月10日, 2020.
  78. 彦坂 秀, 関 翔悟, 武田 一哉, 戸田 智基, "微分可能全域通過フィルタを用いたダイナミックレンジ圧縮," 日本音響学会2020念秋季研究発表会, 2-2-7, 講演論文集, pp. 775-776, 9月10日, 2020.
  79. 木下 裕磨, 小野 順貴, "深層自己符号化器に基づく音響特徴量の離散符号化," 日本音響学会2020念秋季研究発表会, 3-U2-7, 講演論文集, pp. 321-322, 9月11日, 2020.
  80. 渡邊 千紘, 亀岡 弘和, "スペクトログラムテンプレートの学習に基づく解釈可能な深層クラスタリング法," 2020年度人工知能学会全国大会(第34会), 2Q1-GS-10-01, 論文集, Vol. JSAI2020, pp. 1-4, 6月10日, 2020.
  81. 戸田 智基, "音声変換技術と音声生成機能拡張への応用," 電子情報通信学会2020年総合大会, TK-4-1, 講演論文集, pp. 34-35, 3月18日, 2020.
  82. Robin Scheibler, Nobutaka Ono, "FIVE: fast independent vector extraction via auxiliary function optimization with globally optimal updates," 日本音響学会2020年春季研究発表会, 1-1-18, 講演論文集, pp. 205-206, 3月16日, 2020.
  83. 小野 順貴, シャイブラー ロビン, "分離行列のランク1更新によるブラインド音源分離," 日本音響学会2020年春季研究発表会, 1-1-19, 講演論文集, pp. 207-208, 3月16日, 2020.
  84. 安原 和輝, Yi-Chiao Wu, Patrick Lumban Tobing, 松永 悟行, 大谷 大和, 戸田 智基, "テキスト音声合成におけるポストフィルタとしてのWaveNetボコーダ学習法," 日本音響学会2020年春季研究発表会, 1-2-5, 講演論文集, pp. 1051-1052, 3月16日, 2020.
  85. 山岡 洸瑛, シャイブラー ロビン, 小野 順貴, 若林 佑幸, "補助関数法を用いた相互相関の最大化によるサンプリング周波数ミスマッチ推定," 日本音響学会2020年春季研究発表会, 2-1-14, 講演論文集, pp. 249-252, 3月17日, 2020.
  86. 中嶋 大志, シャイブラー ロビン, 若林 佑幸, 小野 順貴, "分離ベクトル同時更新による独立低ランク行列分析の収束性と性能向上の検討," 日本音響学会2020年春季研究発表会, 3-1-15, 講演論文集, pp. 309-312, 3月18日, 2020.
  87. 小野 順貴, "機械学習における乗算を用いない次元削減," 電子情報通信学会信号処理研究会, 技術研究報告, Vol. 119, No. 440, SIP2019-106, pp. 21-26, 3月2日, 2020.【令和2年度電子情報通信学会信号処理研究会賞(受賞者:小野 順貴)】
  88. 中谷 輝, Patrick Lumban Tobing, 武田 一哉, 戸田 智基, "CycleVAEを用いたクロスリンガル声質変換," 電子情報通信学会音声研究会, 技術研究報告, Vol. 119, No. 441, SP2019-88, pp. 219-224, 3月3日, 2020.
  89. 関 翔悟, 高田 萌絵, 武田 一哉, 戸田 智基, "変分自己符号化器を用いた空気・体内伝導音の結合音源モデリングに基づく半教師あり自己発声音強調・抑圧," 電子情報通信学会音声研究会, 技術研究報告, Vol. 119, No. 441, SP2019-89, pp. 225-230, 3月3日, 2020.
  90. 李 莉, 亀岡 弘和, 井上 翔太, 牧野 昭二, "多チャンネル変分自己符号化器法による任意話者の音源分離," 電子情報通信学会応用音響研究会, 技術研究報告, Vol. 119, No. 334, EA2019-77, pp. 79-84, 12月5日, 2019.
 

その他発表

  1. 渡邊 千紘, 亀岡 弘和, "話者共通スペクトログラムテンプレートの畳み込み機構をもつ説明可能な深層音声分離法", 情報論的学習理論ワークショップ(IBIS2020), オンライン, 2020年11月26日.
  2. 戸田 智基, "音声コミュニケーションにおける機能拡張," 名古屋大学 情報学シンポジウム2020, 愛知, 2020年1月27日.
  3. 戸田 智基, "周りに内緒で通話できるか," 名古屋大学高等教育院 卓越・先端・次世代シンポジウム, 愛知, 2020年1月14日.
  4. Tomoki Toda, "Creation of cooperative human augmentation techniques in sound media communication," 第2回JST-ANR連携「共生インタラクション」国際シンポジウム2019, 東京, 2019年12月2日.
 

博士論文

  1. Yi-Chiao Wu, "Incorporating prior knowledge on speech production mechanism into neural speech waveform generation," 情報学研究科知能システム学専攻博士論文, Mar. 25, 2021.
  2. Patrick Lumban Tobing, "High-quality and flexible voice conversion techniques based on statistical spectral and waveform modeling," 情報科学研究科メディア科学専攻博士論文, Mar. 25, 2020.
  3. Shogo Seki, "A study on utilization of prior knowledge for underdetermined source separation and its application," 情報学研究科知能システム学専攻博士論文, Mar. 25, 2020.