JVS corpus: free Japanese multi-speaker voice corpus

Abstract

Thanks to improvements in machine learning techniques, including deep learning, speech synthesis is becoming a machine learning task. To accelerate speech synthesis research, we are developing Japanese voice corpora reasonably accessible from not only academic institutions but also commercial companies. In 2017, we released the JSUT corpus, which contains 10 hours of reading-style speech uttered by a single speaker, for end-to-end text-to-speech synthesis. For more general use in speech synthesis research, e.g., voice conversion and multi-speaker modeling, in this paper, we construct the JVS corpus, which contains voice data of 100 speakers in three styles (normal, whisper, and falsetto). The corpus contains 30 hours of voice data including 22 hours of parallel normal voices. This paper describes how we designed the corpus and summarizes the specifications. The corpus is available at our project page.

References in corpus (3)

• WaveNet: A Generative Model for Raw Audio
• Sampling-based speech parameter generation using moment-matching networks
• DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis

Cited by in corpus (13)

• ESPnet2-TTS: Extending the Edge of TTS Research
• SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech
• Heterogeneous Target Speech Separation
• ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit
• Towards Listening to 10 People Simultaneously: An Efficient Permutation Invariant Training of Audio Source Separation Using Sinkhorn's Algorithm
• Vowels and Prosody Contribution in Neural Network Based Voice Conversion Algorithm with Noisy Training Data
• Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes
• Improved Prosody from Learned F0 Codebook Representations for VQ-VAE Speech Waveform Reconstruction
• RWCP-SSD-Onomatopoeia: Onomatopoeic Word Dataset for Environmental Sound Synthesis
• High-Fidelity and Low-Latency Universal Neural Vocoder based on Multiband WaveRNN with Data-Driven Linear Prediction for Discrete Waveform Modeling
• JVS-MuSiC: Japanese multispeaker singing-voice corpus
• JSSS: free Japanese speech corpus for summarization and simplification
• Lifter Training and Sub-band Modeling for Computationally Efficient and High-Quality Voice Conversion Using Spectral Differentials