Modeling Multi-speaker Latent Space To Improve Neural TTS: Quick Enrolling New Speaker And Enhancing Premium Voice

Abstract

Neural TTS has shown it can generate high quality synthesized speech. In this paper, we investigate the multi-speaker latent space to improve neural TTS for adapting the system to new speakers with only several minutes of speech or enhancing a premium voice by utilizing the data from other speakers for richer contextual coverage and better generalization. A multi-speaker neural TTS model is built with the embedded speaker information in both spectral and speaker latent space. The experimental results show that, with less than 5 minutes of training data from a new speaker, the new model can achieve an MOS score of 4.16 in naturalness and 4.64 in speaker similarity close to human recordings (4.74). For a well-trained premium voice, we can achieve an MOS score of 4.5 for out-of-domain texts, which is comparable to an MOS of 4.58 for professional recordings, and significantly outperforms single speaker result of 4.28.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydeng2018modeling

Related papers

• Improving The Quality Of Neural TTS Using Long-form Content And Multi-speaker Multi-style Modeling (2022)3.58
• Combining Speakers Of Multiple Languages To Improve Quality Of Neural Voices (2021)5.24
• Training Multi-speaker Neural Text-to-speech Systems Using Speaker-imbalanced Speech Corpora (2019)8.09
• Efficient Neural Speech Synthesis For Low-resource Languages Through Multilingual Modeling (2020)8.60
• Non-autoregressive TTS With Explicit Duration Modelling For Low-resource Highly Expressive Speech (2021)8.82
• Deep Voice 2: Multi-speaker Neural Text-to-speech (2017)0.00
• Ganspeech: Adversarial Training For High-fidelity Multi-speaker Speech Synthesis (2021)10.07
• Adapting TTS Models For New Speakers Using Transfer Learning (2021)0.00