提出可重构的语音编解码器，解决重编码失真问题。
LILAC: An Idempotent Neural Speech Codec
- 通过全卷积结构实现编解码器恒等性设计
- 在9.375 Hz、0.75 kbit/s下保持4.14~4.24的音质评分
- 适合需要多次重编码的语音生成流水线
神经语音编解码器广泛应用于语音生成与编辑。然而现有方法不具备恒等性：在本文测试的十二个基线系统中，每种配置在一次解码-重编码流程中平均重写至少15%的标记。这导致在需重复重编码的流水线中出现累积失真。我们提出LILAC，一种在24 kHz采样率下以9.375 Hz和0.75 kbit/s运行的全卷积语音编解码器，其恒等性由构造保证——对任意有效标记流进行解码后重编码，结果完全一致。LILAC在保持竞争性音质的同时实现恒等性，在LibriSpeech和LibriTTS-R测试集上分别达到UTMOS 4.14和4.24，媲美现有亚1 kbit/s的最先进神经语音编解码器。
原文摘要 · Abstract (English)
Neural Audio Codecs are widely adopted in speech generation and editing. However, existing neural audio codecs are not idempotent: across the paper's twelve baseline systems, every configuration tested rewrites, on average, at least 15% of its tokens in a single decode-re-encode pass. This poses a problem for utilizing Neural Audio Codecs as token interfaces in pipelines where re-encoding decoded outputs can occur. We present LILAC, a fully convolutional 24 kHz speech codec at 9.375 Hz and 0.75 kbit/s that is codec idempotent by construction; re-encoding the decoded audio of any valid token stream returns the identical stream. LILAC achieves idempotency while maintaining competitive quality, reaching UTMOS 4.14 and 4.24 on LibriSpeech and LibriTTS-R test sets, comparable to SOTA sub-1 kbit/s Neural Audio Codecs.
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。