Masashi Unoki 研究室

主宰者：Masashi Unoki

北陸先端科学技術大学院大学

AI 要約（直近 5 年の研究成果）

本研究室は、人間の聴覚システムの仕組みを計算モデルで再現し、それを応用した音声・音響信号処理に取り組んでいます。聴覚の末梢部（外耳・中耳・内耳）から中枢部にかけての情報処理を数式や機械学習で模倣することで、聴覚損失者の音声理解度予測、音声情動認識、機械異音検知など、様々な実問題への解決策を開発しています。具体的には、聴力低下による周波数や時間分解能の低下をシミュレートしたり、時間周波数領域での変調成分（スペクトロテンポラル・モジュレーション）を特徴として抽出したりするアプローチを用いています。さらに、深層学習と組み合わせることで、ノイズ環境下での音声検出、スピーチスパッフィング（音声を偽装したなりすまし）検知、合成音声の真偽判定といった音声セキュリティ分野の課題にも対応しています。加えて、人間の会話における適応現象（エントレインメント）の定量化や、音声の知覚品質評価、防音室の容積推定など、聴覚理論の知見を多角的に応用した研究も展開しています。これらは全て、「人間の耳がどのように音を処理しているのか」という基礎的な理解に基づいており、音響信号処理の基盤となる学問領域を形成しています。

※ 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）

[2026] Speech Intelligibility Prediction Inspired by Processing Auditory Information for Hearing-Impaired Listeners
DOI: https://doi.org/10.1109/access.2026.3706536
[2026] Comprehensive Evaluation of VAD-Based and STM-Based Speech Detection Under Heavy Noise Conditions
DOI: https://doi.org/10.2299/jsp.30.115
[2025] Anomalous Sound Detection Using Time-Frequency Derivative of Instantaneous Phase Features
DOI: https://doi.org/10.1109/apsipaasc65261.2025.11249328
[2025] Study on Signal Processing Techniques in Protecting Voice Personae Against Speech Synthesis Systems
DOI: https://doi.org/10.1109/apsipaasc65261.2025.11249218
[2025] Modeling Multi-Level Hearing Loss for Speech Intelligibility Prediction
DOI: https://doi.org/10.1109/waspaa66052.2025.11230956
[2025] Culture-Aware Multimodal Personality Prediction using Audio, Pose, and Cultural Embeddings
DOI: https://doi.org/10.1145/3747327.3764911
[2025] Unsupervised Anomalous Sound Detection Focused on Timbral-Related Features
DOI: https://doi.org/10.23919/eusipco63237.2025.11226702
[2025] Can the spectral representation of the auditory peripheral system explain vowel production changes under noises masking lower formants?
DOI: https://doi.org/10.1121/10.0039109
[2025] Lightweight Speech Intelligibility Prediction with Spectro-Temporal Modulation for Hearing-Impaired Listeners
DOI: https://doi.org/10.21437/clarity.2025-1
[2025] Integrating Linguistic and Acoustic Cues for Machine Learning-Based Speech Intelligibility Prediction in Hearing Impairment
DOI: https://doi.org/10.21437/clarity.2025-7

続きを表示（残り 90 件）

[2025] Important Modulation Frequency Components of Temporal Amplitude Envelope Contributing to Vocal Emotion Perception
DOI: https://doi.org/10.1044/2025_jslhr-24-00825
[2025] Robust Multilingual Audio Deepfake Detection Through Hybrid Modeling
DOI: https://doi.org/10.1145/3733102.3736706
[2025] Fine-tuning TitaNet-Large Model for Speaker Anonymization Attacker Systems
DOI: https://doi.org/10.1109/icassp49660.2025.10888822
[2025] Sound levels in the operating theatre resulting from hammering during cementless total hip arthroplasty
DOI: https://doi.org/10.1016/j.jos.2024.12.007
[2025] Machine Anomalous Sound Detection Using Spectral-Temporal Modulation Representations Derived From Machine-Specific Filterbanks
DOI: https://doi.org/10.1109/taslpro.2025.3570956
[2025] Ability of Human Auditory Perception to Distinguish Human-Imitated Speech
DOI: https://doi.org/10.1109/access.2025.3526631
[2025] Enhancing Speech Emotion Recognition With Conditional Emotion Feature Diffusion and Progressive Interleaved Learning Strategy
DOI: https://doi.org/10.1109/taslpro.2025.3561606
[2025] Speech Intelligibility Prediction Using Binaural Processing for Hearing Loss
DOI: https://doi.org/10.1109/access.2025.3538708
[2025] ディープフェイク音声の脅威と対策について
DOI: https://doi.org/10.1587/bplus.19.239
[2025] Effects of delayed auditory feedback on consonant, vowel, and mora timing in Japanese speech
DOI: https://doi.org/10.1250/ast.e25.57
[2025] Enhancing Model Robustness for Deepfake Singing Voice Detection through Data Augmentation
DOI: https://doi.org/10.2299/jsp.29.221
[2024] Unsupervised Anomalous Sound Detection Using Timbral and Human Voice Disorder-Related Acoustic Features
DOI: https://doi.org/10.1109/apsipaasc63619.2025.10848563
[2024] Detecting Spoof Voices in Asian Non-Native Speech: An Indonesian and Thai Case Study
DOI: https://doi.org/10.1109/apsipaasc63619.2025.10848707
[2024] Anomalous Machine Sound Detection Based on Time Domain Gammatone Spectrogram Feature and IDNN Model
DOI: https://doi.org/10.1109/apsipaasc63619.2025.10849225
[2024] BEES: A New Acoustic Task for Blended Emotion Estimation in Speech
DOI: https://doi.org/10.1109/apsipaasc63619.2025.10848842
[2024] Blind Estimation of Room Volume from Reverberant Speech Based on the Modulation Transfer Function
DOI: https://doi.org/10.1109/apsipaasc63619.2025.10849066
[2024] Transformers and audio detection tasks: An overview
DOI: https://doi.org/10.1016/j.dsp.2024.104956
[2024] Study on Inaudible Speech Watermarking Method Based on Spread-Spectrum Using Linear Prediction Residue
DOI: https://doi.org/10.2299/jsp.28.309
[2024] Weak hammering sounds are associated with postoperative subsidence in cementless total hip arthroplasty
DOI: https://doi.org/10.1007/s00264-024-06351-w
[2024] Deepfake Speech Detection: Approaches from Acoustic Features to Deep Neural Networks
DOI: https://doi.org/10.1587/transinf.2024mui0001
[2024] Are Recent Deep Learning-Based Speech Enhancement Methods Ready to Confront Real-World Noisy Environments?
DOI: https://doi.org/10.21437/interspeech.2024-129
[2024] Linear Model Approach for Investigating the Comprehensive Entrainment in Conversation
DOI: https://doi.org/10.2299/jsp.28.133
[2024] Computational models of auditory sensation important for sound quality on basis of either gammatone or gammachirp auditory filterbank
DOI: https://doi.org/10.1016/j.apacoust.2024.109914
[2024] Hybrid Transformer Architectures With Diverse Audio Features for Deepfake Speech Classification
DOI: https://doi.org/10.1109/access.2024.3478731
[2024] Potential of Speech-Pathological Features for Deepfake Speech Detection
DOI: https://doi.org/10.1109/access.2024.3447582
[2024] Investigation of Social Factor in Conversational Entrainments
DOI: https://doi.org/10.1109/access.2024.3491857
[2023] Blind Estimation of Speech Transmission Index and Room Acoustic Parameters by Using Extended Model of Room Impulse Response Derived From Speech Signals
DOI: https://doi.org/10.1109/access.2023.3276327
[2023] Speaker Verification Using Distance Based on Principal Component Analysis for Household Scenario Adaptation
DOI: https://doi.org/10.1109/rivf60135.2023.10471805
[2023] RIVF'23 Message from Host University
DOI: https://doi.org/10.1109/rivf60135.2023.10471822
[2023] Robust voice activity detection using an auditory-inspired masked modulation encoder based convolutional attention network
DOI: https://doi.org/10.1016/j.specom.2023.103024
[2023] Computational model for predicting sound quality metrics using loudness model based on gammatone/gammachirp auditory filterbank and its applications
DOI: https://doi.org/10.3397/in_2023_0861
[2023] Study on suppression effect of air-conducted sound by bone-conducted sound
DOI: https://doi.org/10.3397/in_2023_0778
[2023] ThaiSpoof: A Database for Spoof Detection in Thai Language
DOI: https://doi.org/10.1109/isai-nlp60301.2023.10354956
[2023] Deepfake-speech Detection with Pathological Features and Multilayer Perceptron Neural Network
DOI: https://doi.org/10.1109/apsipaasc58517.2023.10317331
[2023] Analysis of Spectro-Temporal Modulation Representation for Deep-Fake Speech Detection
DOI: https://doi.org/10.1109/apsipaasc58517.2023.10317309
[2023] Contribution of modulation spectral features for cross-lingual speech emotion recognition under noisy reverberant conditions
DOI: https://doi.org/10.1109/apsipaasc58517.2023.10317449
[2023] Incorporating the Digit Triplet Test in A Lightweight Speech Intelligibility Prediction for Hearing Aids
DOI: https://doi.org/10.1109/apsipaasc58517.2023.10317260
[2023] Increasing Speech Intelligibility by Mimicking Professional Announcers’ Voices and Its Physical Correlates
DOI: https://doi.org/10.1109/apsipaasc58517.2023.10317261
[2023] Non-intrusive speech intelligibility prediction using an auditory periphery model with hearing loss
DOI: https://doi.org/10.1016/j.apacoust.2023.109663
[2023] Data-driven Non-uniform Filterbanks Based on F-ratio for Machine Anomalous Sound Detection
DOI: https://doi.org/10.23919/eusipco58844.2023.10289922
[2023] Auditory Model Optimization with Wavegram-CNN and Acoustic Parameter Models for Nonintrusive Speech Intelligibility Prediction in Hearing Aids
DOI: https://doi.org/10.23919/eusipco58844.2023.10289742
[2023] A Non-Intrusive Speech Intelligibility Prediction Using Binaural Cues and Time-Series Model with One-Hot Listener Embedding
DOI: https://doi.org/10.21437/clarity.2023-1
[2023] Consonant-emphasis Method Incorporating Robust Consonant-section Detection to Improve Intelligibility of Bone-conducted speech
DOI: https://doi.org/10.21437/interspeech.2023-2568
[2023] Contributions of Temporal Modulation Cues in Temporal Amplitude Envelope of Speech to Urgency Perception
DOI: https://doi.org/10.3390/app13106239
[2023] An Improved Optimal Transport Kernel Embedding Method with Gating Mechanism for Singing Voice Separation and Speaker Identification
DOI: https://doi.org/10.1109/icassp49357.2023.10096651
[2023] Methods for improving word intelligibility of bone-conducted speech by using bone-conduction headphones
DOI: https://doi.org/10.1016/j.apacoust.2023.109337
[2023] Personality trait estimation in group discussions using multimodal analysis and speaker embedding
DOI: https://doi.org/10.1007/s12193-023-00401-0
[2023] Method of estimating three-dimensional direction-of-arrival based on monaural modulation spectrum
DOI: https://doi.org/10.1016/j.apacoust.2023.109215
[2023] A Survey of Audio Classification Using Deep Learning
DOI: https://doi.org/10.1109/access.2023.3318015
[2023] A Discriminative Feature Representation Method Based on Cascaded Attention Network With Adversarial Strategy for Speech Emotion Recognition
DOI: https://doi.org/10.1109/taslp.2023.3245401
[2023] Anomalous Sound Detection for Industrial Machines Using Acoustical Features Related to Timbral Metrics
DOI: https://doi.org/10.1109/access.2023.3294334
[2023] Contributions of Jitter and Shimmer in the Voice for Fake Audio Detection
DOI: https://doi.org/10.1109/access.2023.3301616
[2023] Music Theory-Inspired Acoustic Representation for Speech Emotion Recognition
DOI: https://doi.org/10.1109/taslp.2023.3289312
[2023] Phase-Aware Speech Enhancement With Complex Wiener Filter
DOI: https://doi.org/10.1109/access.2023.3341919
[2023] Unsupervised Deep Unfolded Representation Learning for Singing Voice Separation
DOI: https://doi.org/10.1109/taslp.2023.3302237
[2022] Reconstruction of speech spectrogram based on non-invasive EEG signal
DOI: https://doi.org/10.1109/iscslp57327.2022.10038234
[2022] Dialogue scenario classification based on social factors
DOI: https://doi.org/10.1109/iscslp57327.2022.10037880
[2022] Contribution of Timbre and Shimmer Features to Deepfake Speech Detection
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9980281
[2022] Speech Intelligibility Prediction for Hearing Aids Using an Auditory Model and Acoustic Parameters
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9980000
[2022] Analysis of Amplitude and Frequency Perturbation in the Voice for Fake Audio Detection
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9980028
[2022] Investigation of noise-reverberation-robustness of modulation spectral features for speech-emotion recognition
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9980032
[2022] Deep Hashing for Speaker Identification and Retrieval Based on Auditory Sparse Representation
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9980015
[2022] Learning Emotion Information for Expressive Speech Synthesis Using Multi-resolution Modulation-filtered Cochleagram
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9979810
[2022] F<sub>0</sub> Modification via PV-TSM Algorithm for Speaker Anonymization Across Gender
DOI: https://doi.org/10.23919/apsipaasc55919.2022.9979993
[2022] Study on the perception of nonlinguistic information of noise-vocoded speech under noise and/or reverberation conditions
DOI: https://doi.org/10.1250/ast.43.306
[2022] Replay Attack Detection in Automatic Speaker Verification Using Gammatone Cepstral Coefficients and ResNet-Based Model
DOI: https://doi.org/10.2299/jsp.26.171
[2022] Contribution of Common Modulation Spectral Features to Vocal-Emotion Recognition of Noise-Vocoded Speech in Noisy Reverberant Environments
DOI: https://doi.org/10.3390/app12199979
[2022] Speaker anonymization by pitch shifting based on time-scale modification
DOI: https://doi.org/10.21437/spsc.2022-7
[2022] Data Augmentation Using McAdams-Coefficient-Based Speaker Anonymization for Fake Audio Detection
DOI: https://doi.org/10.21437/interspeech.2022-10088
[2022] Vector-quantized Variational Autoencoder for Phase-aware Speech Enhancement
DOI: https://doi.org/10.21437/interspeech.2022-443
[2022] Global Signal-to-noise Ratio Estimation Based on Multi-subband Processing Using Convolutional Neural Network
DOI: https://doi.org/10.21437/interspeech.2022-154
[2022] Automatic Mean Opinion Score Estimation with Temporal Modulation Features on Gammatone Filterbank for Speech Assessment
DOI: https://doi.org/10.21437/interspeech.2022-528
[2022] Method for improving the word intelligibility of presented speech using bone-conduction headphones
DOI: https://doi.org/10.21437/interspeech.2022-10463
[2022] Bone-conducted Speech Enhancement Using Vector-quantized Variational Autoencoder and Gammachirp Filterbank Cepstral Coefficients
DOI: https://doi.org/10.23919/eusipco55093.2022.9909731
[2022] Relationship Between Speakers' Physiological Structure and Acoustic Speech Signals: Data-Driven Study Based on Frequency-Wise Attentional Neural Network
DOI: https://doi.org/10.23919/eusipco55093.2022.9909649
[2022] Detection of Brain Network Communities During Natural Speech Comprehension From Functionally Aligned EEG Sources
DOI: https://doi.org/10.3389/fncom.2022.919215
[2022] Blind Speech Watermarking Method with Frame Self-Synchronization Based on Spread-Spectrum Using Linear Prediction Residue
DOI: https://doi.org/10.3390/e24050677
[2021] Audio Information Hiding in Sub-signals by deploying Singular Spectrum Analysis and Psychoacoustic Model
[2021] Evolving Multi-Resolution Pooling CNN for Monaural Singing Voice Separation
DOI: https://doi.org/10.1109/taslp.2021.3051331
[2021] Replay Attack Detection in Automatic Speaker Verification Based on ResNeWt18 with Linear Frequency Cepstral Coefficients
DOI: https://doi.org/10.1109/isai-nlp54397.2021.9678164
[2021] Computational Models of Sharpness and Fluctuation Strength Using Loudness Models Composed of Gammatone and Gammachirp Auditory Filterbanks
DOI: https://doi.org/10.2299/jsp.25.141
[2021] Speaker anonymization by modifying fundamental frequency and x-vector singular value
DOI: https://doi.org/10.1016/j.csl.2021.101326
[2021] Speech Watermarking Method Using McAdams Coefficient Based on Random Forest Learning
DOI: https://doi.org/10.3390/e23101246
[2021] Blind estimation of speech transmission index and room acoustic parameters based on the extended model of room impulse response
DOI: https://doi.org/10.1016/j.apacoust.2021.108372
[2021] Crossfire Conditional Generative Adversarial Networks for Singing Voice Extraction
DOI: https://doi.org/10.21437/interspeech.2021-433
[2021] Blind Estimation of Room Acoustic Parameters and Speech Transmission Index using MTF-based CNNs
DOI: https://doi.org/10.23919/eusipco54536.2021.9616044
[2021] Robust Voice Activity Detection Using a Masked Auditory Encoder Based Convolutional Neural Network
DOI: https://doi.org/10.1109/icassp39728.2021.9415045
[2021] Multi-resolution modulation-filtered cochleagram feature for LSTM-based dimensional emotion recognition from speech
DOI: https://doi.org/10.1016/j.neunet.2021.03.027
[2021] Synchronous Multi-Bit Audio Watermarking Based on Phase Shifting
DOI: https://doi.org/10.1109/icassp39728.2021.9414307
[2021] Frequency-specific Brain Network Dynamics during Perceiving Real Words and Pseudowords
DOI: https://doi.org/10.1109/iscslp49672.2021.9362052

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）