Menu Japanese
  • Home
  • Members
  • Projects
  • Publications
  • Access
  • Internal Only

Speech and Audio Processing Laboratory

Sakyo-ku, Kyoto 606-8501, Japan

  • Kyoto University
  • School of Informatics
  • Intelligence Science and Technology Course
  • Home
  • Members
  • Projects
  • Publications
    • Journal Papers
    • Conference Papers
  • Access
  • Internal Only

Human-Robot Dialogue
Spoken dialogue models and systems, which will behave like and naturally interact with human beings.

Speech Recognition and Understanding
Automatic speech recognition (ASR) of real-world conversations, including emotional and speaker attribute information.

Audio Scene Analysis
Analysis of the audio environment, where multiple persons and a variety of sound sources exist.

Human-Robot Dialogue
Spoken dialogue models and systems, which will behave like and naturally interact with human beings.

PrevNext
Start
Stop
1
2
3
4

Introduction of Laboratory

  • Members
  • Projects
  • Publications
    • Journal Papers
    • Conference Papers
  • Access

Joint Projects

  • Avatar Symbiotic Society Project (Moonshot Goal R&D 1)
  • Communicative Intelligence Project funded by MEXT
  • Human-Robot Interaction Project funded by JST ERATO
  • Smart Posterboard Project funded by JST CREST
  • Automatic Transcription System for the Japanese Parliament (Diet)
  • Japanese Dictation Toolkit funded by IPA, Japan
  • Spoken Dialogue Project funded by MEXT

Databases & Tools Available

  • Literature Search on Speech Processing
  • Speech Recognition Software: Julius
  • Open Source Robot Audition Software HARK

Copyright © 2015-2025 Prof. Kawahara Lab, Kyoto University, all rights reserved.