TY - GEN
T1 - Espnet-TTS
T2 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
AU - Hayashi, Tomoki
AU - Yamamoto, Ryuichi
AU - Inoue, Katsuki
AU - Yoshimura, Takenori
AU - Watanabe, Shinji
AU - Toda, Tomoki
AU - Takeda, Kazuya
AU - Zhang, Yu
AU - Tan, Xu
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - This paper introduces a new end-to-end text-to-speech (E2E-TTS) toolkit named ESPnet-TTS, which is an extension of the open-source speech processing toolkit ESPnet. The toolkit supports state-of-the-art E2E-TTS models, including Tacotron 2, Transformer TTS, and FastSpeech, and also provides recipes inspired by the Kaldi automatic speech recognition (ASR) toolkit. The recipes are based on the design unified with the ESPnet ASR recipe, providing high reproducibility. The toolkit also provides pre-trained models and samples of all of the recipes so that users can use it as a baseline. Furthermore, the unified design enables the integration of ASR functions with TTS, e.g., ASR-based objective evaluation and semi-supervised learning with both ASR and TTS models. This paper describes the design of the toolkit and experimental evaluation in comparison with other toolkits. The experimental results show that our models can achieve state-of-the-art performance comparable to the other latest toolkits, resulting in a mean opinion score (MOS) of 4.25 on the LJSpeech dataset. The toolkit is publicly available at https://github.com/espnet/espnet.
AB - This paper introduces a new end-to-end text-to-speech (E2E-TTS) toolkit named ESPnet-TTS, which is an extension of the open-source speech processing toolkit ESPnet. The toolkit supports state-of-the-art E2E-TTS models, including Tacotron 2, Transformer TTS, and FastSpeech, and also provides recipes inspired by the Kaldi automatic speech recognition (ASR) toolkit. The recipes are based on the design unified with the ESPnet ASR recipe, providing high reproducibility. The toolkit also provides pre-trained models and samples of all of the recipes so that users can use it as a baseline. Furthermore, the unified design enables the integration of ASR functions with TTS, e.g., ASR-based objective evaluation and semi-supervised learning with both ASR and TTS models. This paper describes the design of the toolkit and experimental evaluation in comparison with other toolkits. The experimental results show that our models can achieve state-of-the-art performance comparable to the other latest toolkits, resulting in a mean opinion score (MOS) of 4.25 on the LJSpeech dataset. The toolkit is publicly available at https://github.com/espnet/espnet.
KW - Open-source
KW - end-to-end
KW - text-to-speech
UR - http://www.scopus.com/inward/record.url?scp=85089215967&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089215967&partnerID=8YFLogxK
U2 - 10.1109/ICASSP40776.2020.9053512
DO - 10.1109/ICASSP40776.2020.9053512
M3 - Conference contribution
AN - SCOPUS:85089215967
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 7654
EP - 7658
BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 May 2020 through 8 May 2020
ER -