Papers/2609.28727
🧪 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
80%
1h ago

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.
← Back to all papers