Institute of Information Science Academia Sinica
Topic: Academia Sinica / Kyoto University Joint Workshop on Speech and Music Processing
Date: 2019-09-11 (Wed)
Location: Auditorium 106 at IIS new Building

Time

Title

Speaker

14:00~14:25

Opening Talk

Mark Liao

14:25~14:50

Toward Human-level Spoken Dialogue with Android ERICA

Tatsuya Kawahara

14:50~15:10

Variational Autoencoder-based Voice Conversion

Hsin-Ming Wang

15:10~15:30

A Goal-driven Noise Reduction Method and Its Application to Assistive Hearing Devices

Yu Tsao

15:30~15:40

Coffee break

 

15:40~16:00

Recent Development on Music Transcription and Synchronization

Li Su

16:00~16:20

Learning to Generate Jazz and Pop Piano Music from Audio via MIR Techniques

Yi-Hsuan Yang

16:20~16:40

Statistical Music Analysis, Composition, and Arrangement Based on Music Language Models

Kazuyoshi Yoshii

16:40~17:00

Towards Audio-to-Symbolic Piano Transcription: Modelling In-Depth Structures of Music

Eita Nakamura

17:00~17:30

Discussion and Closing