# PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMs

arXiv: https://arxiv.org/abs/2609.28727 · HTML: https://mlsanity.com/paper/2609.28727/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2102.01547/) (2021)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [CTC-Assisted LLM-Based Contextual ASR](https://mlsanity.com/paper/2411.06437/) (2024)
- [Contextualization of ASR with LLM using phonetic retrieval-based augmentation](https://mlsanity.com/paper/2409.15353/) (2024)
- [Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter](https://mlsanity.com/paper/2406.07096/) (2024)
- [Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducer](https://mlsanity.com/paper/2311.08966/) (2023)
- [Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer](https://mlsanity.com/paper/2306.04076/) (2023)
- [Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval](https://mlsanity.com/paper/2411.00664/) (2024)
- [WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasing](https://mlsanity.com/paper/2506.01263/) (2025)
- [MFA-KWS: Effective Keyword Spotting with Multi-head Frame-asynchronous Decoding](https://mlsanity.com/paper/2505.19577/) (2025)
- [Dual Data Scaling for Robust Two-Stage User-Defined Keyword Spotting](https://mlsanity.com/paper/2510.10740/) (2025)
- [Effective User-defined Keyword Spotting with Dual-stage Matching, Multi-modal Enrollment, and Continual Adaptation](https://mlsanity.com/paper/2605.22120/) (2026)

## Abstract (arXiv)

Contextual biasing improves rare-word recognition in speech large language models (SpeechLLMs), but efficiently exploiting large bias lists remains challenging. We propose PTC-Bias, a two-stage framework based on phoneme-level temporal competition. At the prefill stage, PTC Retrieval performs frame-synchronous phoneme decoding and temporal competition among candidate pronunciations, producing a compact bias-word shortlist and corresponding speech intervals. After SpeechLLM decoding, PTC Correction conducts a second local competition between the retrieved candidates and mismatched transcript spans within these intervals. Selective correction reduces near-homophone and word-segmentation errors while preserving correct transcriptions. Both stages share the same phoneme posteriors and require no additional SpeechLLM forward pass. Experiments on LibriSpeech show consistent gains across two SpeechLLMs and bias lists of up to 2000 words. With Prompt-SLAM-ASR-7B and 2000 bias words, PTC-Bias reduces B-WER by 23.4%/23.9% relative to CTC-Filter on test-clean/test-other, while keeping U-WER nearly unchanged.