🧪 Test?View on arXiv
PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMs
Not provided in the content
bias retrievalspeech recognitionphoneme decoding
2609.28727
Builder Relevance
1h ago80%
Abstract
PTC-Bias proposes a two-stage framework that improves rare-word recognition in SpeechLLMs through phoneme-level temporal competition.
Reality Card
Core Claim
PTC-Bias reduces B-WER by 23.4%/23.9% relative to CTC-Filter on test-clean/test-other while maintaining U-WER.
Method / Result
PTC-Bias achieves a 23.4% reduction in B-WER with 2000 bias words.
Limitations
The paper does not specify the authors, which may affect reproducibility and validation of results.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.