no code implementations • 6 Nov 2022 • JIhwan Lee, Jae-Sung Bae, Seongkyu Mun, Heejin Choi, Joun Yeop Lee, Hoon-Young Cho, Chanwoo Kim
With the recent developments in cross-lingual Text-to-Speech (TTS) systems, L2 (second-language, or foreign) accent problems arise.
2 code implementations • 27 Jun 2022 • Taejun Bak, Junmo Lee, Hanbin Bae, Jinhyeok Yang, Jae-Sung Bae, Young-Sun Joo
Therefore, in this paper, we investigate the relationship between these artifacts and GAN-based vocoders and propose a GAN-based vocoder, called Avocodo, that allows the synthesis of high-fidelity speech with reduced artifacts.
no code implementations • 8 Apr 2022 • Jae-Sung Bae, Jinhyeok Yang, Tae-Jun Bak, Young-Sun Joo
This paper proposes a hierarchical and multi-scale variational autoencoder-based non-autoregressive text-to-speech model (HiMuV-TTS) to generate natural speech with diverse speaking styles.
no code implementations • 4 Apr 2022 • JIhwan Lee, Joun Yeop Lee, Heejin Choi, Seongkyu Mun, Sangjun Park, Jae-Sung Bae, Chanwoo Kim
Two proposed modules are added to the end-to-end TTS framework: an intonation predictor and an intonation encoder.
no code implementations • 29 Jun 2021 • Jae-Sung Bae, Tae-Jun Bak, Young-Sun Joo, Hoon-Young Cho
Therefore, to improve the modeling performance of the TNA-TTS model we propose a hierarchical Transformer structure-based text encoder and audio decoder that are designed to accommodate the characteristics of each module.
1 code implementation • 29 Jun 2021 • Taejun Bak, Jae-Sung Bae, Hanbin Bae, Young-Ik Kim, Hoon-Young Cho
Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models.
no code implementations • 29 Jun 2021 • Jinhyeok Yang, Jae-Sung Bae, Taejun Bak, Youngik Kim, Hoon-Young Cho
Recent advances in neural multi-speaker text-to-speech (TTS) models have enabled the generation of reasonably good speech quality with a single model and made it possible to synthesize the speech of a speaker with limited training data.
no code implementations • 4 Mar 2021 • Hanbin Bae, Jae-Sung Bae, Young-Sun Joo, Young-Ik Kim, Hoon-Young Cho
Second, the GST-TTS model with an auxiliary quality classifier is trained with the filtered speech and a small amount of clean speech.