Tomoki Toda 研究室

主宰者：Tomoki Toda

名古屋大学

AI 要約（直近 5 年の研究成果）

本研究室は、音声と音響信号の生成・変換・評価に関する幅広い研究を展開しています。主要なテーマは、テキストや音声特徴から自然な音声波形を合成するニューラルボコーダー（音声合成技術）の開発です。音声の基本周波数制御や高周波成分の忠実な再現、計算効率の向上などの課題に対して、源音フィルタモデルなどの音響理論に基づいた手法を深層学習と組み合わせることで、高品質で制御性の高い合成音声の実現を目指しています。並行して、喉頭摘出者が用いる電気喉頭音声の自然化処理や、音声認識の誤り補正など、実際の医療応用や応用技術の課題にも取り組んでいます。これらの研究では、言語的情報と音響的情報を統合した表現学習、領域適応技術、自動音韻抽出など、複数の専門知識を活用したアプローチが採られています。さらに、音楽生成や異常音検知といった音響信号処理の拡張領域でも成果を上げており、音声品質評価や聴覚知覚の分析を通じた客観的な評価手法の開発も進めています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（100 件）

[2025] Wavehax: Aliasing-Free Neural Waveform Synthesis Based on 2D Convolution and Harmonic Prior for Reliable Complex Spectrogram Estimation
DOI: https://doi.org/10.1109/taslpro.2025.3624985
[2025] Music Similarity Representation Learning Focusing on Individual Instruments with Source Separation and Human Preference
DOI: https://doi.org/10.1561/116.20250016
[2025] STUDY ON AUTOMATIC GENERATION OF LECTURE VIDEOS BASED ON CONTENT ANALYSIS OF LECTURE SLIDES
DOI: https://doi.org/10.33965/celda2025_202509c044
[2025] Hierarchical Symbolic Music Generation with Variational Autoencoder-Based Bar-Wise Feature Sequences
DOI: https://doi.org/10.1109/apsipaasc65261.2025.11249414
[2025] Disfluency Disentanglement Enhancement in Spoken-Text-Style Transfer for Spontaneous Speech Synthesis
DOI: https://doi.org/10.1109/apsipaasc65261.2025.11248977
[2025] Investigation of the Effectiveness of Converted Speech Auditory Feedback in Low-Latency Real-Time Voice Conversion
DOI: https://doi.org/10.1109/apsipaasc65261.2025.11249417
[2025] SHEET: A Multi-purpose Open-source Speech Human Evaluation Estimation Toolkit
DOI: https://doi.org/10.21437/interspeech.2025-1977
[2025] Speaker-Aware Multi-Task Learning for Speech Emotion Recognition
DOI: https://doi.org/10.21437/interspeech.2025-1439
[2025] Who, When, and What: Leveraging the ``Three Ws'' Concept for Emotion Recognition in Conversation
DOI: https://doi.org/10.21437/interspeech.2025-1433
[2025] CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models
DOI: https://doi.org/10.21437/interspeech.2025-943

続きを表示（残り 90 件）

[2025] GIA-MIC: Multimodal Emotion Recognition with Gated Interactive Attention and Modality-Invariant Learning Constraints
DOI: https://doi.org/10.21437/interspeech.2025-2696
[2025] Relationship between objective and subjective perceptual measures of speech in individuals with head and neck cancer
DOI: https://doi.org/10.21437/interspeech.2025-1127
[2025] Unifying Listener Scoring Scales: Comparison Learning Framework for Speech Quality Assessment and Continuous Speech Emotion Recognition
DOI: https://doi.org/10.21437/interspeech.2025-1435
[2025] GST-BERT-TTS: Prosody Prediction Without Accentual Labels For Multi-Speaker TTS Using BERT With Global Style Tokens
DOI: https://doi.org/10.21437/interspeech.2025-1098
[2025] Eigenvoice Synthesis based on Model Editing for Speaker Generation
DOI: https://doi.org/10.21437/interspeech.2025-277
[2025] Improving Electrolaryngeal Speech Enhancement via a Representation Learning Method Based on Integrated Text and Speech Representations
DOI: https://doi.org/10.1109/embc58623.2025.11254511
[2025] Mora-Level Prosody Prediction for Text-to-Speech Using Japanese BERT Without Accentual Labels
DOI: https://doi.org/10.1109/icassp49660.2025.10887607
[2025] XPPG-PCA: Reference-Free Automatic Speech Severity Evaluation With Principal Components
DOI: https://doi.org/10.1109/jstsp.2025.3617859
[2025] Resolving Domain Mismatches in Electrolaryngeal Speech Enhancement With Linguistic Intermediates
DOI: https://doi.org/10.1109/jstsp.2025.3584195
[2025] Recovery from Electrolaryngeal Speech to Original Voice : Save the Voice Project
DOI: https://doi.org/10.2468/jbes.76.108
[2025] Generalized sound field interpolation for freely spaced microphone arrays in rotation-robust beamforming
DOI: https://doi.org/10.1016/j.apacoust.2025.110706
[2025] E2EPref: An end-to-end preference-based framework for speech quality assessment to alleviate bias in direct assessment scores
DOI: https://doi.org/10.1016/j.csl.2025.101799
[2025] Investigation of perceptual music similarity focusing on each instrumental part
DOI: https://doi.org/10.1109/icassp49660.2025.10887810
[2025] Mandarin speech reconstruction from surface electromyography based on generative adversarial networks
DOI: https://doi.org/10.1016/j.medntd.2025.100359
[2025] Target Speaker Extraction under Noisy Underdetermined Conditions Using Conditional Variational Autoencoder, Global Style Token, and Neural Postfilter
DOI: https://doi.org/10.1561/116.20240067
[2025] Serial-OE: Anomalous Sound Detection Based on Serial Method with Outlier Exposure Capable of Using Small Amounts of Anomalous Data for Training
DOI: https://doi.org/10.1561/116.20240060
[2025] Learning Separated Representations for Instrument-based Music Similarity
DOI: https://doi.org/10.1561/116.20250013
[2025] Fast Neural Vocoder With Fundamental Frequency Control Using Finite Impulse Response Filters
DOI: https://doi.org/10.1109/taslpro.2025.3564048
[2025] Sequence-to-sequence Voice Conversion-based Techniques for Electrolaryngeal Speech Enhancement in Noisy and Reverberant Conditions
DOI: https://doi.org/10.1561/116.20240094
[2025] PMF-CEC: Phoneme-Augmented Multimodal Fusion for Context-Aware ASR Error Correction With Error-Specific Selective Decoding
DOI: https://doi.org/10.1109/taslpro.2025.3577356
[2025] Pretraining and Fine-Tuning Techniques for Electrolaryngeal Speech Enhancement Based on Sequence-to-Sequence Voice Conversion
DOI: https://doi.org/10.1109/taslpro.2025.3577374
[2025] Nonparallel Spoken-Text-Style Transfer for Linguistic Expression Control in Speech Generation
DOI: https://doi.org/10.1109/taslpro.2024.3522757
[2025] Predicting Fundamental Frequency Patterns in Electrolaryngeal Speech Using Automated Phoneme Extraction
DOI: https://doi.org/10.1109/access.2025.3564648
[2025] Sequence-Wise Speech Waveform Modeling via Backpropagation Optimization of Quasi-Harmonic Parameters
DOI: https://doi.org/10.1109/taslpro.2024.3522784
[2025] Phoneme-Level Duration Controllable Neural Text-to-Speech With Phoneme Embedding Skip Connection and Modified Gaussian Duration Modeling
DOI: https://doi.org/10.1109/access.2025.3585135
[2025] QHARMA-GAN: Quasi-Harmonic Neural Vocoder Based on Autoregressive Moving Average Model
DOI: https://doi.org/10.1109/taslpro.2025.3603847
[2025] An Investigation of Noisy-to-noisy Voice Conversion Performance in Various Noisy Conditions
DOI: https://doi.org/10.1561/116.20250008
[2025] Analysis and Extension of Noisy-target Training for Unsupervised Target Signal Enhancement
DOI: https://doi.org/10.1561/116.20250018
[2025] Improving Anomalous Sound Detection Through Pseudo-anomalous Set Selection and Pseudo-label Utilization Under Unlabeled Conditions
DOI: https://doi.org/10.1561/116.20250017
[2025] Text- and Speech-style Control for Lecture Speech Generation Focusing on Disfluency
DOI: https://doi.org/10.1561/116.20250005
[2025] SiFi-GAN: Combining Source-Filter Modeling and Upsampling-Based High-Fidelity Neural Vocoder for Fast and Pitch-Controllable Speech Synthesis
DOI: https://doi.org/10.1587/transinf.2025edp7142
[2025] Speaker Privacy and Security in the Big Data Era: Protection and Defense Against Deepfake
DOI: https://doi.org/10.1109/apsipaasc65261.2025.11249028
[2024] Convnext-TTS And Convnext-VC: Convnext-Based Fast End-To-End Sequence-To-Sequence Text-To-Speech And Voice Conversion
DOI: https://doi.org/10.1109/icassp48485.2024.10446890
[2024] FIRNet: Fundamental Frequency Controllable Fast Neural Vocoder With Trainable Finite Impulse Response Filter
DOI: https://doi.org/10.1109/icassp48485.2024.10446960
[2024] End-to-End Mandarin Speech Reconstruction Based on Ultrasound Tongue Images Using Deep Learning
DOI: https://doi.org/10.1109/tnsre.2024.3520498
[2024] Two-stage Framework for Robust Speech Emotion Recognition Using Target Speaker Extraction in Human Speech Noise Conditions
DOI: https://doi.org/10.1109/apsipaasc63619.2025.10848943
[2024] Improved Architecture for High-resolution Piano Transcription to Efficiently Capture Acoustic Characteristics of Music Signals
DOI: https://doi.org/10.1109/apsipaasc63619.2025.10848780
[2024] Audio Difference Learning for Audio Captioning
DOI: https://doi.org/10.1109/icassp48485.2024.10448085
[2024] Multi-Task Learning Approaches for Music Similarity Representation Learning Based on Individual Instrument Sounds
DOI: https://doi.org/10.1109/apsipaasc63619.2025.10849029
[2024] The Voicemos Challenge 2024: Beyond Speech Quality Prediction
DOI: https://doi.org/10.1109/slt61566.2024.10832295
[2024] CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detection
DOI: https://doi.org/10.21437/interspeech.2024-2242
[2024] Multimodal Fusion of Music Theory-Inspired and Self-Supervised Representations for Improved Emotion Recognition
DOI: https://doi.org/10.21437/interspeech.2024-2350
[2024] Quantifying the effect of speech pathology on automatic and human speaker verification
DOI: https://doi.org/10.21437/interspeech.2024-1400
[2024] Challenge of Singing Voice Synthesis Using Only Text-To-Speech Corpus With FIRNet Source-Filter Neural Vocoder
DOI: https://doi.org/10.21437/interspeech.2024-2504
[2024] Embedding Learning for Preference-based Speech Quality Assessment
DOI: https://doi.org/10.21437/interspeech.2024-1243
[2024] 2DP-2MRC: 2-Dimensional Pointer-based Machine Reading Comprehension Method for Multimodal Moment Retrieval
DOI: https://doi.org/10.21437/interspeech.2024-1633
[2024] QHM-GAN: Neural Vocoder based on Quasi-Harmonic Modeling
DOI: https://doi.org/10.21437/interspeech.2024-2371
[2024] Exploring the Robustness of Text-to-Speech Synthesis Based on Diffusion Probabilistic Models to Heavily Noisy Transcriptions
DOI: https://doi.org/10.21437/interspeech.2024-2337
[2024] Discriminative Neighborhood Smoothing for Generative Anomalous Sound Detection
DOI: https://doi.org/10.23919/eusipco63174.2024.10715201
[2024] Mandarin Speech Reconstruction from Tongue Motion Ultrasound Images based on Generative Adversarial Networks
DOI: https://doi.org/10.1109/embc53108.2024.10781847
[2024] Robust Sequence-to-sequence Voice Conversion for Electrolaryngeal Speech Enhancement in Noisy and Reverberant Conditions
DOI: https://doi.org/10.1109/embc53108.2024.10781979
[2024] MF-AED-AEC: Speech Emotion Recognition by Leveraging Multimodal Fusion, Asr Error Detection, and Asr Error Correction
DOI: https://doi.org/10.1109/icassp48485.2024.10446548
[2024] Electrolaryngeal Speech Intelligibility Enhancement through Robust Linguistic Encoders
DOI: https://doi.org/10.1109/icassp48485.2024.10447197
[2024] Fast Neural Speech Waveform Generative Models With Fully-Connected Layer-Based Upsampling
DOI: https://doi.org/10.1109/access.2024.3366707
[2024] Dual-Channel Target Speaker Extraction Based on Conditional Variational Autoencoder and Directional Information
DOI: https://doi.org/10.1109/taslp.2024.3376154
[2024] Multi-Speaker Text-to-Speech Training With Speaker Anonymized Data
DOI: https://doi.org/10.1109/lsp.2024.3482701
[2024] Unequally Spaced Sound Field Interpolation for Rotation-Robust Beamforming
DOI: https://doi.org/10.1109/taslp.2024.3410879
[2024] An Investigation of Fundamental Frequency Pattern Prediction for Japanese Electrolaryngeal Speech Enhancement Based on Frame-Wise Phoneme Representations
DOI: https://doi.org/10.1109/access.2024.3384973
[2024] Pretraining and Adaptation Techniques for Electrolaryngeal Speech Recognition
DOI: https://doi.org/10.1109/taslp.2024.3402557
[2023] Noisy-to-Noisy Voice Conversion Under Variations of Noisy Condition
DOI: https://doi.org/10.1109/taslp.2023.3313426
[2023] The Singing Voice Conversion Challenge 2023
DOI: https://doi.org/10.1109/asru57964.2023.10389671
[2023] The Voicemos Challenge 2023: Zero-Shot Subjective Speech Quality Prediction for Multiple Domains
DOI: https://doi.org/10.1109/asru57964.2023.10389763
[2023] WaveNeXt: ConvNeXt-Based Fast Neural Vocoder Without ISTFT layer
DOI: https://doi.org/10.1109/asru57964.2023.10389765
[2023] Improving Severity Preservation of Healthy-to-Pathological Voice Conversion With Global Style Tokens
DOI: https://doi.org/10.1109/asru57964.2023.10389707
[2023] A Comparative Study of Voice Conversion Models With Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023
DOI: https://doi.org/10.1109/asru57964.2023.10389779
[2023] Preoperative Recording of Original Voices in Laryngectomized Patients : The Save the Voice Project
DOI: https://doi.org/10.5426/larynx.35.142
[2023] An Analysis of Personalized Speech Recognition System Development for the Deaf and Hard-of-Hearing
DOI: https://doi.org/10.1109/apsipaasc58517.2023.10317318
[2023] Evaluating Methods for Ground-Truth-Free Foreign Accent Conversion
DOI: https://doi.org/10.1109/apsipaasc58517.2023.10317592
[2023] Semi-supervised Multimodal Emotion Recognition with Consensus Decision-making and Label Correction
DOI: https://doi.org/10.1145/3607865.3613182
[2023] Directional Target Speaker Extraction under Noisy Underdetermined Conditions through Conditional Variational Autoencoder with Global Style Tokens
DOI: https://doi.org/10.1109/waspaa58266.2023.10248146
[2023] Differentiable Representation of Warping Based on Lie Group Theory
DOI: https://doi.org/10.1109/waspaa58266.2023.10248099
[2023] Sound Field Interpolation with Unsupervised Calibration for Freely Spaced Circular Microphone Array in Rotation-Robust Beamforming
DOI: https://doi.org/10.23919/eusipco58844.2023.10289792
[2023] Emotion Awareness in Multi-utterance Turn for Improving Emotion Prediction in Multi-Speaker Conversation
DOI: https://doi.org/10.21437/interspeech.2023-1236
[2023] Analysis of Mean Opinion Scores in Subjective Evaluation of Synthetic Speech Based on Tail Probabilities
DOI: https://doi.org/10.21437/interspeech.2023-1285
[2023] E2E-S2S-VC: End-To-End Sequence-To-Sequence Voice Conversion
DOI: https://doi.org/10.21437/interspeech.2023-2518
[2023] Reverberation-Controllable Voice Conversion Using Reverberation Time Estimator
DOI: https://doi.org/10.21437/interspeech.2023-1356
[2023] Preference-based training framework for automatic speech quality assessment using deep neural network
DOI: https://doi.org/10.21437/interspeech.2023-589
[2023] Text-To-Speech Synthesis Based on Latent Variable Conversion Using Diffusion Probabilistic Model and Variational Autoencoder
DOI: https://doi.org/10.1109/icassp49357.2023.10094298
[2023] Intermediate Fine-Tuning Using Imperfect Synthetic Speech for Improving Electrolaryngeal Speech Recognition
DOI: https://doi.org/10.1109/icassp49357.2023.10095931
[2023] Representation of Vocal Tract Length Transformation Based on Group Theory
DOI: https://doi.org/10.1109/icassp49357.2023.10095239
[2023] Two-Stage Training Method for Japanese Electrolaryngeal Speech Enhancement Based on Sequence-to-Sequence Voice Conversion
DOI: https://doi.org/10.1109/slt54892.2023.10023033
[2023] Harmonic-Net: Fundamental Frequency and Speech Rate Controllable Fast Neural Vocoder
DOI: https://doi.org/10.1109/taslp.2023.3275032
[2023] High-Fidelity and Pitch-Controllable Neural Vocoder Based on Unified Source-Filter Networks
DOI: https://doi.org/10.1109/taslp.2023.3313410
[2023] ED-CEC: Improving Rare word Recognition Using ASR Postprocessing Based on Error Detection and Context-Aware Error Correction
DOI: https://doi.org/10.1109/asru57964.2023.10389661
[2022] Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition
DOI: https://doi.org/10.21437/interspeech.2022-10043
[2022] Interpretable Control for Emotional Text-to-Speech System toward Development of Sympathetic Educational-Support Robots
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9980201
[2022] Music Similarity Calculation of Individual Instrumental Sounds Using Metric Learning
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9979944
[2022] Sequence-wise Optimization for Quasi-Harmonic Speech Waveform Modeling
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9980023
[2022] A Cyclical Approach to Synthetic and Natural Speech Mismatch Refinement of Neural Post-filter for Low-cost Text-to-speech System
DOI: https://doi.org/10.1561/116.00000020
[2022] Unified Source-Filter GAN with Harmonic-plus-Noise Source Excitation Generation
DOI: https://doi.org/10.21437/interspeech.2022-11130

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（100 件）

科研費（0 件）

所属学会・役職（0 件）