Improving Seq2Seq TTS Frontends With Transcribed Speech Audio

Siqi Sun, Korin Richmond, Hao Tang 0002. Improving Seq2Seq TTS Frontends With Transcribed Speech Audio. IEEE Transactions on Audio, Speech & Language Processing, 31:1940-1952, 2023. [doi]

Authors

Siqi Sun

This author has not been identified. Look up 'Siqi Sun' in Google

Korin Richmond

This author has not been identified. Look up 'Korin Richmond' in Google

Hao Tang 0002

This author has not been identified. Look up 'Hao Tang 0002' in Google