M5-TTS: A Mini-Scale Multilingual and Multi-Dialect Text-to-Speech Language Model with Multi-Token Prediction
eess.AS, cs.SD
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/ASLP-lab/M5-TTShttps:
Project page: https://aslp-lab.github.io/M5-TTS-Demo-Pagehttps://huggingface.co/spaces/ASLP-lab/M5-TTS-Space
Terminology
Sources
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- WenetSpeech-Chuan: A Large-Scale Sichuanese Corpus with Rich Annotation for Dialectal Speech Processing
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- The Llama 3 Herd of Models
- Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation
- Qwen3-TTS Technical Report
- Robust Speech Recognition via Large-Scale Weak Supervision
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability
- Qwen3-ASR Technical Report
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
- Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
- MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder
- VoxCPM2 Technical Report
Related papers
- WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling
- From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model
- Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy
- pyFDN: A Python Toolbox for Feedback Delay Network Design, Analysis, and Optimization
- GigaSpeechBench: A Real-World Multilingual Speech-to-Text Benchmark
- DM-ASR: Diarization-aware Multi-speaker ASR with Unified Offline and Online Decoding with Large Language Models