AISHELL-3

AISHELL-3 is a large-scale and high-fidelity multi-speaker Mandarin speech corpus published by Beijing Shell Shell Technology Co.,Ltd. It can be used to train multi-speaker Text-to-Speech (TTS) systems.The corpus contains roughly 85 hours of emotion-neutral recordings spoken by 218 native Chinese mandarin speakers and

Papers using AISHELL-3 (7)

M3-TTS: Multi-modal DiT Alignment & Mel-latent for Zero-shot High-fidelity Speech Synthesis2025Enhanced exemplar autoencoder with cycle consistency loss in any-to-one voice conversion2022 · 1 citesLanguage-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models2022AdaVocoder: Adaptive Vocoder for Custom Voice2022PSVRF: Learning to restore Pitch-Shifted Voice without reference2022TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training2022PMVC: Data Augmentation-Based Prosody Modeling for Expressive Voice Conversion2023