発表文献

2026年度に発表された文献の一覧

学術論文誌

  1. J. Mi, X. Shi, D. Ma, J. He, T. Fujimura, T. Toda, "Robust speech emotion recognition under human speech noise," Computer Speech and Language, Vol. 100, Article 101987, pp. 1-16, Apr. 2026.
  2. T. Komatsu, H. Munakata, Y. Ishikawa, K. Takeda, T. Toda, "Semi-supervised text-audio contrastive learning method using pseudo-text input," APSIPA Transactions on Signal and Information Processing, Vol. 15, No. 1, pp. 183-198, Apr. 2026.
  3. Y. Hashizume, T. Toda, "Investigation of perceptual music similarity based on individual instrumental parts by large-scale listening test," APSIPA Transactions on Signal and Information Processing, Vol. 15, No. 1, pp. 249-269, Apr. 2026.
  4. J. Feng, Y. Yasuda, T. Toda, "An investigation of the robustness of flow- and diffusion-based speech generation models on noisy transcriptions," APSIPA Transactions on Signal and Information Processing, Vol. 15, No. 1, pp. 270-292, Apr. 2026.
  5. W.-C. Huang, E. Cooper, T. Toda, "MOS-Bench: benchmarking generalization abilities of subjective speech quality assessment models," IEEE Transactions on Audio, Speech and Language Processing, Vol. 34, pp. 2385-2397, Apr. 2026.
  6. X. Shi, X. Li, T. Toda, "Emotion similarity and shift: modeling temporal dynamic interactions for emotion prediction in conversation," IEEE Transactions on Audio, Speech and Language Processing, Vol. 34, pp. 2552-2567, Apr. 2026.
  7. R. Yoneyama, T. Toda, "SiFi-GAN: combining source-filter modeling and upsampling-based high-fidelity neural vocoder for fast and pitch-controllable speech synthesis," IEICE Trans. Inf. and Syst., Vol. E109-D, No. 6, pp. 945-956, June 2026.
  8. D. Ma, J. Mi, F. Li, L.P. Violeta, J. He, W.-C. Huang, K. Kobayashi, T. Toda, "Advancing electrolaryngeal speech enhancement through speech-text representation learning," IEEE Transactions on Biomedical Engineering, Vol. 73, No. 8, pp. 2861-2875, Aug. 2026.
  9. J. Feng, Y. Yasuda, T. Toda, "CTC score-based transcription quality annotation for stable text-to-speech synthesis training on noisy transcriptions," APSIPA Transactions on Signal and Information Processing, Vol. 15, No. 1, pp. 532-555, Sep. 2026.
  10. C.-H. Hu, Y. Yasuda, T. Toda, "Investigation of preference-based speech quality assessment by integrating adaptive pair selection and pseudo-labeling," APSIPA Transactions on Signal and Information Processing, Vol. 15, No. 1, pp. 722-752, Oct. 2026.
  11. J. Wang, T. Toda, "Investigating statistical and spatial loss functions for geometry-aware unsupervised virtual microphone estimation in multi-source environments," APSIPA Transactions on Signal and Information Processing, Vol. 15, No. 1, pp. 753–773, Oct. 2026.
　

国際会議

  1. T. Imamura, T. Komatsu, H. Munakata, T. Toda, "Audio-visual feature fusion for calibrating relevance scores of video moment retrieval," Proc. IEEE ICASSP, pp. 5551-5555, Barcelona, Spain, May 2026.
  2. L.P. Violeta, X. Zhang, J. Shi, Y. Yasuda, W.-C. Huang, Z. Wu, T. Toda, "The singing voice conversion challenge 2025: from singer identity conversion to singing style conversion," Proc. IEEE ICASSP, pp. 17707-17711, Barcelona, Spain, May 2026.
  3. J. Wang, T. Toda, "From fixed positions to free-form signals: Virtual Microphone signal estimation for general-purpose spatial audio processing," Proc. IEEE ICASSP, pp. 21011-21015, Barcelona, Spain, May 2026.
  4. H. Munakata, T. Imamura, T. Nishimura, T. Komatsu, "CASTELLA: long audio dataset with captions and temporal boundaries," Proc. IEEE ICASSP, pp. 15352-15356, Barcelona, Spain, May 2026.
  5. B. Xu, W. Zhang, D. Ma, J. Liang, Z. Sun, Z. Lei, "Modeling long-tail relations in the operating room via in-context multimodal learning," Proc. ICML, 10 pages, Seoul, South Korea, July 2026.
  6. H. Folkertsma, T. Tienkamp, S. de Visscher, M. Witjes, R. van Son, J. Guo, B.M. Halpern, "Improving automatic speech recognition for speakers treated for oral cancer using data augmentation and LLM error correction," Proc. EMBC, pp. 627-631, Tronto, Canada, July 2026.
  7. T. Imamura, Y. Hashizume, W.-C. Huang, T. Toda, "Incorporating signal processing-based knowledge for music similarity representation learning based on individual instrument sounds," Proc. EUSIPCO, pp. 46-50, Bruges, Belgium, Sep. 2026.
  8. K. Ogita, R. Yoneyama, W.-C. Huang, T. Toda, "Evaluating VAE-SiFiGAN under large-scale training and noisy conditions with data selection using F0 extraction error estimation," Proc. EUSIPCO, pp. 466-470, Bruges, Belgium, Sep. 2026.
  9. T. Fujimura, Y. Masuyama, G. Wichern, C. Boeddeker, J. Richter, and J. Le Roux, "NABEATs: Noise-aware audio representation learning," Proc. IWAENC, 5 pages, Cremona, Italy, Sep. 2026.
  10. X. Shi, X. Li, T. Toda, "Leveraging modality-specific label distributions for enhanced multimodal emotion recognition," Proc. INTERSPEECH, pp. 1909-1913, Sydney, Australia, Sep. 2026.
  11. J. Mi, D. Ma, T. Toda, "Learning emotion-discriminative representations for zero-shot cross-lingual speech emotion recognition," Proc. INTERSPEECH, pp. 2292-2296, Sydney, Australia, Sep. 2026.
  12. E. Cooper, X. Gao, T. Okamoto, T. Toda, N. Chen, H. Kawai, "A dataset for listener assessment of emotional synthesized speech," Proc. INTERSPEECH, pp. 4265-4270, Sydney, Australia, Sep. 2026.
  13. M. Murata, K. Miyazaki, T. Koriyama, T. Toda, "Exploring pre-training benefits on phoneme addition through fine-tuning in speech synthesis," Proc. INTERSPEECH, pp. 5384-5388, Sydney, Australia, Sep. 2026.
  14. W. Ren, Y.-C. Lin, W.-C. Huang, E. Cooper, R.E. Zezario, H.-M. Wang, H.-yi Lee, Y. Tsao. "MOS-Bias: from hidden gender bias to gender-aware speech quality assessment," Proc. INTERSPEECH, pp. 6108-6112, Sydney, Australia, Sep. 2026.
  15. W.-C. Huang, N. Sanders, E. Cooper. "CodecMOS-Accent: a MOS benchmark of resynthesized and TTS speech from neural codecs across English accents," Proc. INTERSPEECH, pp. 6130-6135, Sydney, Australia, Sep. 2026.
  16. B.M. Halpern, T. Tienkamp, D. Abur, T. Toda, "PathBench: speech intelligibility benchmark for automatic pathological speech assessment," Proc. INTERSPEECH, pp. 7526-7531, Sydney, Australia, Sep. 2026.
  17. T. Fujimura, G. Wichern, Y. Masuyama, C. Boeddeker, K. Saijo, J. Richter, T. Edo, J. Le Roux, "Anomalous sound detection meets noise-aware self-supervised learning," Proc. DCASE Workshop, pp. 106-110, Boston, USA, Oct. 2026.
  18. T. Edo, G. Wichern, T. Fujimura, C. Boeddeker, Y. Masuyama, J. Richter, K. Saijo, J. Le Roux, "When speech is noise: speech removal for machine anomaly detection," Proc. DCASE Workshop, pp. 111-115, Boston, USA, Oct. 2026.
  19. Y. Guo, J. He, X. Shi, T. Toda, Z. Yang, B. Wang, Y. Taniguchi, "Leveraging LLM-generated explanations for detecting emotionally rewritten fake news," Proc. ACAIT, 8 pages, Chongqing, China, Oct.-Nov. 2026.
　

研究会

  1. デ ポンテス ジェフェルソン マコト, ホワン ウェンチン, 戸田 智基, "モジュール分離型アーキテクチャによるオーディオエフェクト設定逆推定," 情報処理研報, Vol. 2026-MUS-146, No. 8, pp. 1-6, June 2026.【音学シンポジウム2026学生優秀発表賞（受賞者：デ ポンテス ジェフェルソン マコト）】
  2. 浪崎 恭佑, ホワン ウェンチン, 戸田 智基, "聴覚フィードバック音声制御に向けた体内伝導自己聴取音マスキングの調査," 情報処理研報, Vol. 2026-SLP-160, No. 44, pp. 1-6, June 2026.
  3. 齋藤 佑樹, HUANG Wen-Chin, 榎本 悠久, 今井 柊平, "Human Fooling Rateテストに基づく最先端の日本語テキスト音声合成モデルの評価および分析," 情報処理研報, Vol. 2026-MUS-160, No. 60, pp. 1-5, June 2026.
　

大会講演

  1. 中井 淳一, 藤村 拓弥, 浅野 憲司, 若松 智之, 戸田 智基, "説明性向上マルチモーダルAIによるMOCの異常予見～潜在的異常発見に向けたアテンションによる実験的分析～," 人工知能学会全国大会論文集, 1I3-GS-10f-02, 4 pages, June 2026.
  2. 阿久根 遙, 郡家 彩加, 後藤 駿太, 飯尾 尊優, 宮下 敦志, 戸田 智基, 住岡 英信, 塩見 昌裕, "赤ちゃん型ロボットにおける最適な応答発話頻度の設計・評価," 日本ロボット学会学術講演会予稿集, RSJ2026AC1C1-02, 3 pages, Sep. 2026.
  3. 兼子 政孝, ホワン ウェンチン, 戸田 智基, "モノラル音声による車内着座位置推定における音響特徴量の比較," 音講論, 2-8-8, pp. 259-260, Sep. 2026.
  4. HUANG Wen-Chin, 戸田 智基, "UTMOSへの攻撃," 音講論, 1-7-5, pp. 1413-1414, Sep. 2026.
  5. 山下 陽生, 岡本 拓磨, 高島 遼一, 大谷 大和, 滝口 哲也, 戸田 智基, 河井 恒, "Zero-shotテキスト音声合成を用いた日本語訛り英語生成の比較," 音講論, 1-Q-34, pp. 1563-1564, Sep. 2026.
  6. 村田 雅人, 宮崎 晃一, 郡山 知樹, 戸田 智基, "音声合成モデルにおけるモデルマージを用いた話者補間手法の検討," 音講論, 1-Q-37, pp. 1571-1572, Sep. 2026.
  7. 石川 雄斗, ホワン ウェンチン, 戸田 智基, "口唇動画からの音声合成における深度情報の有効性検証," 音講論, 1-Q-63, pp. 1651-1654, Sep. 2026.
  8. 大谷 大和, 岡本 拓磨, 戸田 智基, 河井 恒, "音声生成タスクに着目した自己教師あり学習に基づく音声表現の特性解析," 音講論, 2-P-53, pp. 1799-1802, Sep. 2026.
  9. デ ポンテス ジェフェルソン マコト, ホワン ウェンチン, 戸田 智基, "モジュール分離型オーディオエフェクト設定逆推定における学習戦略," 音講論, 1-1-4, pp. 1853-1854, Sep. 2026.
　

その他発表

  1. S. Chen, T. Toda, "QHARMA-GAN: quasi-harmonic neural vocoder based on autoregressive moving average model," IEEE ICASSP, SPS journal paper presentation, Barcelona, Spain, May 2026.
  2. D. Ma, L.P. Violeta, K. Kobayashi, T. Toda, "Pretraining and fine-tuning techniques for electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion," IEEE ICASSP, SPS journal paper presentation, Barcelona, Spain, May 2026.
  3. J. He, X. Shi, C.-H. Hu, J. Mi, X. Li, T. Toda, "M4SER: multimodal, multirepresentation, multitask, and multistrategy learning for speech emotion recognition," IEEE ICASSP, SPS journal paper presentation, Barcelona, Spain, May 2026.
  4. B.M. Halpern, T.B. Tienkamp, T. Rebernik, R.J.J.H. van Son, S.A.H.J. de Visscher, M.J.H. Witjes, D. Abur, T. Toda, "XPPG-PCA: reference-free automatic speech severity evaluation with principal components," IEEE ICASSP, SPS journal paper presentation, Barcelona, Spain, May 2026.
  5. T. Fujimura, G. Wichern, Y. Masuyama, C. Boeddeker, K. Saijo, J. Richter, T. Edo, and J. Le Roux, "The MERL systems for DCASE 2026 challenge task 2," Technical report, DCASE 2026 Challenge Task 2, 5 pages, July 2026.【DCASE 2026 Challenge Task 2 Judges' Award】
  6. 戸田 智基, "名古屋大学キャリア講演会 情報学部コンピュータ科学科," 桑野高校, 三重, July 2026.
  7. 呉 安南, "深層符号化潜在特徴空間への埋め込みに基づく高耐性音声電子透かし法," 第30回東海地区音声関連研究室修士論文中間発表会, 愛知, Sep. 2026.
  8. 浪崎 恭佑, "音声変換における聴覚フィードバック調整のための体内伝導自己聴取音マスキング," 第30回東海地区音声関連研究室修士論文中間発表会, 愛知, Sep. 2026.
  9. 宮司 光梨, "制御性の高いピアノ自動編曲に向けた楽曲難易度推定と難易度付きペアデータの作成," 第30回東海地区音声関連研究室修士論文中間発表会, 愛知, Sep. 2026.【総合1位（受賞者：宮司 光梨）】
  10. 古田 京平, "任意話者を対象とする低遅延リアルタイム音声変換の実現に向けた知識蒸留に関する検討," 第30回東海地区音声関連研究室修士論文中間発表会, 愛知, Sep. 2026.
　

博士論文

  1. ChengHung Hu, "Preference-based speech assessment: methodology, data strategies, and applications," 情報学研究科知能システム学専攻博士論文, Sep. 2026.
  2. Jingyi Feng, "Robust modeling and learning for text-to-speech synthesis with noisy transcriptions," 情報学研究科知能システム学専攻博士論文, Sep. 2026.
  3. Xiaohan Shi, "Computational modeling of emotional expressions, dynamics, and interactions in conversation," 情報学研究科知能システム学専攻博士論文, Sep. 2026.
　

他の年度はこちら