2 citations · 2 across the 8 of their papers we have counts for
8 papers
Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Construction
Kenichi Fujita, Yusuke Ijima
Voice actors often re-read the same script while modifying their delivery in response to performance directions. We study this setting as direction-following TTS, where a system ge…
Investigation for Relative Voice Impression Estimation
Kenichi Fujita, Yusuke Ijima
Paralinguistic and non-linguistic aspects of speech strongly influence listener impressions. While most research focuses on absolute impression scoring, this study investigates rel…
Multi-interaction TTS toward professional recording reproduction
Hiroki Kanagawa, Kenichi Fujita, Aya Watanabe +1
Voice directors often iteratively refine voice actors' performances by providing feedback to achieve the desired outcome. While this iterative feedback-based refinement process is…
Voice Impression Control in Zero-Shot TTS
Kenichi Fujita, Shota Horiguchi, Yusuke Ijima
Para-/non-linguistic information in speech is pivotal in shaping the listeners' impression. Although zero-shot text-to-speech (TTS) has achieved high speaker fidelity, modulating s…
Lightweight Zero-shot Text-to-Speech with Mixture of Adapters
Kenichi Fujita, Takanori Ashihara, Marc Delcroix +1
The advancements in zero-shot text-to-speech (TTS) methods, based on large-scale models, have demonstrated high fidelity in reproducing speaker characteristics. However, these mode…
Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesis
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. Speech rhythm is one of the essentia…
What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis
Takanori Ashihara, Marc Delcroix, Takafumi Moriya +3
Self-supervised learning (SSL) has attracted increased attention for learning meaningful speech representations. Speech SSL models, such as WavLM, employ masked prediction training…
Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters
Kenichi Fujita, Hiroshi Sato, Takanori Ashihara +4
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 sp…