MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer

Nowadays, large-scale text-to-speech (TTS) systems are primarily divided into two types: autoregressive and non-autoregressive. The autoregressive systems have certain deficiencies in robustness and cannot control speech duration. In contrast, non-autoregressive systems require explicit prediction of phone-level duration, which may compromise their naturalness. We introduce the Masked Generative Codec Transformer (MaskGCT), a fully non-autoregressive model for TTS that does not require precise alignment information between text and speech. MaskGCT is a two-stage model: in the first stage, the model uses text to predict semantic tokens extracted from a speech self-supervised learning (SSL) model, and in the second stage, the model predicts acoustic tokens conditioned on these semantic tokens. MaskGCT follows the \textit{mask-and-predict} learning paradigm. During training, MaskGCT learns to predict masked semantic or acoustic tokens based on given conditions and prompts. During inference, the model generates tokens of a specified length in a parallel manner. We scale MaskGCT to a large-scale multilingual dataset with 100K hours of in-the-wild speech. Our experiments demonstrate that MaskGCT achieves superior or competitive performance compared to state-of-the-art zero-shot TTS systems in terms of quality, similarity, and intelligibility while offering higher generation efficiency than diffusion-based or autoregressive TTS models. Audio samples are available at https://maskgct.github.io.

Revisiting IPA-based Cross-lingual Text-to-speech

International Phonetic Alphabet (IPA) has been widely used in cross-lingual text-to-speech (TTS) to achieve cross-lingual voice cloning (CL VC). However, IPA itself has been understudied in cross-lingual TTS. In this paper, we report some empirical findings of building a cross-lingual TTS model using IPA as inputs. Experiments show that the way to process the IPA and suprasegmental sequence has a negligible impact on the CL VC performance. Furthermore, we find that using a dataset including one speaker per language to build an IPA-based TTS system would fail CL VC since the language-unique IPA and tone/stress symbols could leak the speaker information. In addition, we experiment with different combinations of speakers in the training dataset to further investigate the effect of the number of speakers on the CL VC performance.

Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech

In this paper, we present a FastPitch-based non-autoregressive cross-lingual Text-to-Speech (TTS) model built with language independent input representation and monolingual force aligners. We propose a phoneme length regulator that solves the length mismatch problem between language-independent phonemes and monolingual alignment results. Our experiments show that (1) an increasing number of training speakers encourages non-autoregressive cross-lingual TTS model to disentangle speaker and language representations, and (2) variance adaptors of FastPitch model can help disentangle speaker identity from learned representations in cross-lingual TTS. The subjective evaluation shows that our proposed model is able to achieve decent speaker consistency and similarity. We further improve the naturalness of Mandarin-dominated mixed-lingual utterances by utilizing the controllability of our proposed model.