提出单层解耦语音分词器Kanade，实现语音音素与韵律分离。
Kanade: A Simple Disentangled Tokenizer for Spoken Language Modeling
- 单层架构解耦语音信号中的音素与韵律成分
- 在语音重建质量不变前提下达到最优说话人去耦合效果
- 无需额外辅助方法，适合语音合成与语音识别任务
优秀的语言模型始于优秀的分词器。语音建模中，分词器需处理连续信号，其中混合了语言与非语言信息。理想的语音分词器应提取音素与语调，抑制说话人身份等无关信息，并支持高质量语音合成。本文提出Kanade，一种单层解耦语音分词器，可分离出声学常量，生成单一令牌流，完整保留丰富音素与语调信息。该方法无需依赖现有解耦编码器常用的辅助手段。实验表明，Kanade在说话人去耦合和词汇可用性方面达到当前最佳水平，同时保持优异的重建质量。
原文摘要 · Abstract (English)
A good language model starts with a good tokenizer. Tokenization is especially important for speech modeling, which must handle continuous signals that mix linguistic and non-linguistic information. A speech tokenizer should extract phonetics and prosody, suppress linguistically irrelevant information like speaker identity, and enable high-quality synthesis. We present Kanade, a single-layer disentangled speech tokenizer that realizes this ideal. Kanade separates out acoustic constants to create a single stream of tokens that captures rich phonetics and prosody. It does so without the need for auxiliary methods that existing disentangled codecs often rely on. Experiments show that Kanade achieves state-of-the-art speaker disentanglement and lexical availability, while maintaining excellent reconstruction quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。