Maskgct: Zero-shot Text-to-speech With Masked Generative Codec Transformer
2024 · Yuancheng Wang, Haoyue Zhan, Liwei Liu, et al.
Abstract
The recent large-scale text-to-speech (TTS) systems are usually grouped as autoregressive and non-autoregressive systems. The autoregressive systems implicitly model duration but exhibit certain deficiencies in robustness and lack of duration controllability. Non-autoregressive systems require explicit alignment information between text and speech during training and predict durations for linguistic units (e.g. phone), which may compromise their naturalness. In this paper, we introduce Masked Generative Codec Transformer (MaskGCT), a fully non-autoregressive TTS model that eliminates the need for explicit alignment information between text and speech supervision, as well as phone-level duration prediction. 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 mask-an
Authors
(none)
Tags
Stats
Related papers
- Syncspeech: Efficient And Low-latency Text-to-speech Based On Temporal Masked Transformer (2025)0.00
- Mobilespeech: A Fast And High-fidelity Framework For Mobile Zero-shot Text-to-speech (2024)0.00
- Specmaskgit: Masked Generative Modeling Of Audio Spectrograms For Efficient Audio Synthesis And Beyond (2024)0.00
- High Fidelity Text-to-speech Via Discrete Tokens Using Token Transducer And Group Masked Language Model (2024)4.52
- Livespeech: Low-latency Zero-shot Text-to-speech Via Autoregressive Modeling Of Audio Discrete Codes (2024)5.84
- Maskvct: Masked Voice Codec Transformer For Zero-shot Voice Conversion With Increased Controllability Via Multiple Guidances (2025)0.00
- Improved Mask-ctc For Non-autoregressive End-to-end ASR (2020)11.76
- Megatts 3: Sparse Alignment Enhanced Latent Diffusion Transformer For Zero-shot Speech Synthesis (2025)0.00