Preprint: arXiv:2409.17452 (Submitted to ICASSP 2025 ) Abstract Figure Comparison of different systems English TTS Japanese TTS Style controllability samples Pitch control (en) Speed control (en) Pitch control (ja) Speed control (ja) Abstract We propose a novel description-based controllable text-to-speech (TTS) method with cross-lingual control capability. To address the lack of audio-description…
Submitted to IEEE signal processing letters Authors Abstract TTS samples M1 (male) M2 (male) F1 (female) F2 (female) Acknowledgements Authors Ryuichi Yamamoto (LINE Corp.) Min-Jae Hwang (Search Solutions Inc.) Eunwoo Song (NAVER Corp.) Abstract This letter proposes a voicing-aware Parallel Wave- GAN (VA-PWG) vocoder for a neural text-to-speech (TTS) system. To generate a high-quality speech…
Summary コード: https://github.com/r9y9/nnsvs Discussion: https://github.com/r9y9/nnsvs/issues/1 Demo on Google colab 春が来た 春が来た どこに来た。 山に来た 里に来た、野にも来た。花がさく 花がさく どこにさく。山にさく 里にさく、野にもさく。 Your browser does not support the audio element. NNSVS はなに? Neural network-based singing voice synthesis library for research 研究用途を目的とした、歌声合成エンジンを作るためのオープンソースのライブラリを作ることを目指したプロジェクトです。このプロジェクトについて、考えていることをまとめておこうと思います。…
Preprint: arXiv:1910.11480 (accepted to ICASSP 2020 ) Audio samples (Japanese) Audio samples (English) Japanese samples were used in the subjective evaluations reported in our paper. Authors Ryuichi Yamamoto (LINE Corp.) Eunwoo Song (NAVER Corp.) Jae-Min Kim (NAVER Corp.) Abstract We propose Parallel WaveGAN 1 , a distillation-free, fast, and small-footprint waveform generation method using a…
Preprint: arXiv:1904.04472 , Published version: ISCA Archive Interspeech 2019 Authors Ryuichi Yamamoto (LINE Corp.) Eunwoo Song (NAVER Corp.) Jae-Min Kim (NAVER Corp.) Abstract This paper proposes an effective probability density distillation (PDD) algorithm for WaveNet-based parallel waveform generation (PWG) systems. Recently proposed teacher-student frameworks in the PWG system have…
Summary Thank you for coming to see my blog post about WaveNet text-to-speech. Your browser does not support the audio element. 論文リンク: https://arxiv.org/abs/1712.05884 オンラインデモ: Tacotron2: WaveNet-based text-to-speech demo コード r9y9/wavenet_vocoder , Rayhane-mamah/Tacotron-2 音声サンプル: https://r9y9.github.io/wavenet_vocoder/ 三行まとめ 自作WaveNet ( WN ) と既存実装Tacotron 2 (WNを除く) を組み合わせて、英語TTSを作りました…