A unified sequence-to-sequence front-end model for Mandarin text-to-speech synthesis
This work addresses the complexity of building pipeline-based front-end modules for Mandarin TTS systems, offering a more streamlined approach for speech synthesis developers.
The paper tackled the problem of front-end text processing in Mandarin text-to-speech synthesis by proposing a unified sequence-to-sequence model that directly converts raw texts to linguistic features, achieving comparable performance in polyphone disambiguation and prosody word prediction, improving intonation phrase prediction by 0.0738 in F1 score, and producing synthesized speech with a MOS of 4.38, close to human recordings at 4.49.
In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple individual components requires extensive efforts. In this paper, we proposed a unified sequence-to-sequence front-end model for Mandarin TTS that converts raw texts to linguistic features directly. Compared to the pipeline-based front-end, our unified front-end can achieve comparable performance in polyphone disambiguation and prosody word prediction, and improve intonation phrase prediction by 0.0738 in F1 score. We also implemented the unified front-end with Tacotron and WaveRNN to build a Mandarin TTS system. The synthesized speech by that got a comparable MOS (4.38) with the pipeline-based front-end (4.37) and close to human recordings (4.49).