DLLM-TTS：用于语音合成的块离散扩散语言模型
原标题：DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis
AI 摘要
DLLM-TTS 是一种将文本到语音合成（TTS）建模为基于 X-Codec2 神经音频编解码器令牌的条件块离散扩散的框架。该模型将序列分解为块，在块内应用掩码扩散，同时顺序处理块，以学习局部声学一致性和全局文本-语音对齐。在推理时，块内并行令牌预测实现了 0.15 的实时因子（RTF），一个在 20K 小时数据上训练的 0.6B 参数模型在 Seed-TTS-eval 基准上取得了有竞争力的性能，展示了块离散扩散语言模型在并行生成中实现实用且数据高效的语音合成的潜力。
正文节选
Computer Science > Computation and Language Title:DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis View PDF HTML (experimental) Abstract:Current text-to-speech systems face a trade-off: autoregres- sive codec language models produce highly intelligible speech but require large-scale models and training data and decode tokens sequentially, while non-autoregressive approaches im- prove speed at the cost of linguistic accuracy. We present DLLM-TTS, a framew