[Japanese| English]

Research

• • Speech Processing

    • • Speech Conversion: Voice conversion, voice quality control, articulatory controllable speech modification & non-native speech correction

      • Speech Synthesis: Statistical waveform generation, statistical parametric speech synthesis & concatenative speech synthesis

      • Speech Analysis: Speech parameter estimation & para-/non-linguistic information analysis

      • Speech Recognition: Acoustic modeling & body-conducted speech recognition

      • Spoken Dialogue: Statistical dialogue management & response generation

      • Speech Translation: Para-/non-linguistic translation

      • Augmented Speech Production: Speaking-aid, body-conducted speech enhancement & voice changer

      • Speech Assessment: Speech quality assessment & anti-spoofing

  • Music Processing

    • • Singing Voice Analysis: Singing voice quality estimation & description

      • Singing Voice Generation: Singing voice conversion, singing voice synthesis & singing-aid

      • Music Analysis: Acoustic feature estimation, similarity learning, score transcription & score following

      • Music Signal Separation: Monaural/stereo music source separation & vocal extraction

      • Music Generation: Drum pattern modeling, polyphonic music composition

  • Sound Environment Processing

    • • Sound Event Recognition: Polyphonic sound event detection and symbolization & audio captioning

      • Anomalous Sound Detection: Generative & discriminative anomalous sound detection

      • Multichannel Sound Signal Processing: Microphone array processing, air-/body-conducted sound signal processing & noise reduction

Recent Talks

• 2024/07: Invited talk at USTC Frontier Forum on Intelligent Speech Analysis and Generation

  • "Voice conversion techniques to separately control static and dynamic speech characteristics" [Slides]

• 2024/04: Invited talk at RASDAP 2024 "Challenges and Opportunities of Speech Technology Research in the Era of Large Models"

  • "Challenges in leveraging large models for augmented speech production" [Slides]

• 2023/06: Invited talk at Symposium of the 64th Annual Meeting of the Japanese Society of Neurology

  • "The future brought by state-of-the-art speech information processing" [Slides]

• 2021/07: Invited talk at SNL 2021

  • "Interactive voice conversion for augmented speech production" [Slides]

• 2021/01: Invited talk at IEEE SLT 2021

  • "Recent progress on voice conversion: what is next?" [Slides]

Contact

Information Technology Center, Nagoya University

Furo-cho, Chikusa-ku, Nagoya, 464-8601, JAPAN

E-mail: tomoki__at__icts.nagoya-u.ac.jp (Please replace __at__ with @.)

TEL: +81-52-789-4346

[Graduate School of Informatics]

[Nagoya University]