AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines
This provides a valuable dataset and baseline for researchers working on multi-speaker Mandarin TTS, enabling advancements in voice cloning and synthesis, though it is incremental as it builds on existing methods.
The authors introduced AISHELL-3, a large-scale multi-speaker Mandarin speech corpus with 85 hours of recordings from 218 speakers, and developed a baseline TTS system based on Tacotron-2 that achieves high voice similarity in zero-shot voice cloning, as shown by objective metrics like speaker embedding similarity and equal error rate.
In this paper, we present AISHELL-3, a large-scale and high-fidelity multi-speaker Mandarin speech corpus which could 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. Their auxiliary attributes such as gender, age group and native accents are explicitly marked and provided in the corpus. Accordingly, transcripts in Chinese character-level and pinyin-level are provided along with the recordings. We present a baseline system that uses AISHELL-3 for multi-speaker Madarin speech synthesis. The multi-speaker speech synthesis system is an extension on Tacotron-2 where a speaker verification model and a corresponding loss regarding voice similarity are incorporated as the feedback constraint. We aim to use the presented corpus to build a robust synthesis model that is able to achieve zero-shot voice cloning. The system trained on this dataset also generalizes well on speakers that are never seen in the training process. Objective evaluation results from our experiments show that the proposed multi-speaker synthesis system achieves high voice similarity concerning both speaker embedding similarity and equal error rate measurement. The dataset, baseline system code and generated samples are available online.