Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesis

no code implementations • 11 Feb 2024 • Kenichi Fujita, Atsushi Ando, Yusuke Ijima

This paper proposes a speech rhythm-based method for speaker embeddings to model phoneme duration using a few utterances by the target speaker.

Speaker Identification Speech Synthesis

Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters

no code implementations • 10 Jan 2024 • Kenichi Fujita, Hiroshi Sato, Takanori Ashihara, Hiroki Kanagawa, Marc Delcroix, Takafumi Moriya, Yusuke Ijima

The zero-shot text-to-speech (TTS) method, based on speaker embeddings extracted from reference speech using self-supervised learning (SSL) speech representations, can reproduce speaker characteristics very accurately.

Self-Supervised Learning Speech Enhancement +2

Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model

no code implementations • 24 Apr 2023 • Kenichi Fujita, Takanori Ashihara, Hiroki Kanagawa, Takafumi Moriya, Yusuke Ijima

This paper proposes a zero-shot text-to-speech (TTS) conditioned by a self-supervised speech-representation model acquired through self-supervised learning (SSL).

Self-Supervised Learning Speech Synthesis +1