Skip to main content
Search

# Speech Tokenization

1 related articles

Subscribe to updates
  1. arXiv

    Q-SPT compresses speech tokens with learnable queries, achieving the best reconstruction at a matched frame rate and leading downstream recognition and TTS perceptual quality

    The work proposes Q-SPT, a low-frame-rate dual-stream speech tokenizer that uses two separately learned, context-aware query-based compressors for the semantic and acoustic streams, with an autoregressive text loss explicitly supervising the semantic compressor; experiments report the best reconstruction among the evaluated codecs at the same frame rate and, in downstream speech language models, the best speech recognition accuracy and text-to-speech perceptual quality with competitive intelligibility.

You’re all caught up