Picture for Xuan Shi

Xuan Shi

Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio Synthesis Systems?

Nov 25, 2022
Xuan Shi, Erica Cooper, Xin Wang, Junichi Yamagishi, Shrikanth Narayanan

Figure 1 for Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio Synthesis Systems?

Figure 2 for Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio Synthesis Systems?

Figure 3 for Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio Synthesis Systems?

Figure 4 for Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio Synthesis Systems?

* Submitted to ICASSP 2023

Access Paper or Ask Questions

Use of speaker recognition approaches for learning timbre representations of musical instrument sounds from raw waveforms

Jul 24, 2021
Xuan Shi, Erica Cooper, Junichi Yamagishi

Figure 1 for Use of speaker recognition approaches for learning timbre representations of musical instrument sounds from raw waveforms

Figure 2 for Use of speaker recognition approaches for learning timbre representations of musical instrument sounds from raw waveforms

Figure 3 for Use of speaker recognition approaches for learning timbre representations of musical instrument sounds from raw waveforms

Figure 4 for Use of speaker recognition approaches for learning timbre representations of musical instrument sounds from raw waveforms

* Submitted to the IEEE/ACM Transactions on Audio, Speech, and Language Processing

Access Paper or Ask Questions