Machine-learning-based waveform modeling: human voice case

Shinnosuke Takamichi

Presentation information

[J] Oral

S (Solid Earth Sciences ) » S-CG Complex & General

[S-CG55] Driving Solid Earth Science through Machine Learning

Sun. May 21, 2023 1:45 PM - 3:00 PM 302 (International Conference Hall, Makuhari Messe)

convener:Hisahiko Kubo(National Research Institute for Earth Science and Disaster Resilience), Yuki Kodera(Meteorological Research Institute, Japan Meteorological Agency), Makoto Naoi(Kyoto University), Keisuke Yano(The Institute of Statistical Mathematics), Chairperson:Ryoichiro Agata(Japan Agency for Marine-Earth Science and Technology), Keisuke Yano(The Institute of Statistical Mathematics)

1:45 PM - 2:15 PM

[SCG55-07] Machine-learning-based waveform modeling: human voice case

★Invited Papers

*Shinnosuke Takamichi¹ (1.The University of Tokyo)

Keywords:machine learning, waveform modeling, speech

This talk gives waveform modeling using a data-driven approach (machine learning). Waveform modeling is expected to have a wide range of applications such as waveform generation, interpolation, and analysis. The approach to human speech waveforms is known as a successful example. In this talk, the reasons for this success is summarized in terms of the nature of speech and machine learning models. Furthermore, the possibility of transferring the success in speech waveforms to seismic waveforms is discussed.