StreamAlign: Streaming Text-Aligned Speech Tokenization
StreamAlign performs online speech-text alignment by combining character-level RNN-Transducer alignment with word-level ASR guidance, mitigating ASR-LLM vocabulary mismatch while preserving recognition accuracy, and achieves the lowest WER and highest UTMOS among evaluated tokenizers.
Kang-wook Kim, Jinyoung Park, Jinsoo Kim et al.
· 0 citations