11 papers
Spatial-CLAP: Learning Spatially-Aware audio--text Embeddings for Multi-Source Conditions
Kentaro Seki, Yuki Okamoto, Kouei Yamaoka +3
Contrastive language--audio pretraining (CLAP) has achieved remarkable success as an audio--text embedding framework, but existing approaches are limited to monaural or single-sour…
Active Learning for Text-to-Speech Synthesis with Informative Sample Collection
Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki +1
The construction of high-quality datasets is a cornerstone of modern text-to-speech (TTS) systems. However, the increasing scale of available data poses significant challenges, inc…
TTSOps: A Closed-Loop Corpus Optimization Framework for Training Multi-Speaker TTS Models from Dark Data
Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki +1
This paper presents TTSOps, a fully automated closed-loop framework for constructing multi-speaker text-to-speech (TTS) systems from noisy, uncurated web-scale speech data, often r…
SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis
Osamu Take, Shinnosuke Takamichi, Kentaro Seki +2
This paper presents SaSLaW, a spontaneous dialogue speech corpus containing synchronous recordings of what speakers speak, listen to, and watch. Humans consider the diverse environ…
J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling
Wataru Nakata, Kentaro Seki, Hitomi Yanaka +3
Spoken dialogue is essential for human-AI interactions, providing expressive capabilities beyond text. Developing effective spoken dialogue systems (SDSs) requires large-scale, hig…
Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals
Kentaro Seki, Shinnosuke Takamichi, Norihiro Takamune +3
This paper proposes a new task called spatial voice conversion, which aims to convert a target voice while preserving spatial information and non-target signals. Traditional voice…
Noise-Robust Voice Conversion by Conditional Denoising Training Using Latent Variables of Recording Quality and Environment
Takuto Igarashi, Yuki Saito, Kentaro Seki +4
We propose noise-robust voice conversion (VC) which takes into account the recording quality and environment of noisy source speech. Conventional denoising training improves the no…
SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark
Yuki Saito, Takuto Igarashi, Kentaro Seki +4
We present SRC4VC, a new corpus containing 11 hours of speech recorded on smartphones by 100 Japanese speakers. Although high-quality multi-speaker corpora can advance voice conver…
Diversity-based core-set selection for text-to-speech with linguistic and acoustic features
Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki +1
This paper proposes a method for extracting a lightweight subset from a text-to-speech (TTS) corpus ensuring synthetic speech quality. In recent years, methods have been proposed f…
How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics
Joonyong Park, Shinnosuke Takamichi, Tomohiko Nakamura +3
We examine the speech modeling potential of generative spoken language modeling (GSLM), which involves using learned symbols derived from data rather than phonemes for speech analy…
Text-to-speech synthesis from dark data with evaluation-in-the-loop data selection
Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki +1
This paper proposes a method for selecting training data for text-to-speech (TTS) synthesis from dark data. TTS models are typically trained on high-quality speech corpora that cos…