提升语音识别对同音实体的区分能力，让系统更准更鲁棒。
PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation
- 通过声韵特征增强和对比消歧，精准识别同音词
- 在1000个干扰项下中文CER降至4.22%，英文WER为11.14%
- 适合需要高精度命名实体识别的语音应用
自动语音识别系统在处理领域特定命名实体（尤其是同音词）时表现不佳。上下文语音识别虽有改进，但常因实体多样性不足而难以捕捉细微的发音差异。以往方法将实体视为独立标记，导致多词偏置不完整。为此，我们提出基于对比实体消歧的声韵增强鲁棒上下文语音识别方法（PARCO），融合声韵感知编码、对比实体消歧、实体级监督与层级实体过滤机制。这些组件增强了语音区分能力，确保实体完整召回，并在不确定情况下减少误报。实验表明，PARCO在中文AISHELL-1数据集上达到4.22%的词错误率（CER），在英文DATA2数据集上达到11.14%的词错误率（WER），且在1,000个干扰项条件下显著优于基线模型。该方法在跨域数据集如THCHS-30和LibriSpeech上也展现出稳健提升。
原文摘要 · Abstract (English)
Automatic speech recognition (ASR) systems struggle with domain-specific named entities, especially homophones. Contextual ASR improves recognition but often fails to capture fine-grained phoneme variations due to limited entity diversity. Moreover, prior methods treat entities as independent tokens, leading to incomplete multi-token biasing. To address these issues, we propose Phoneme-Augmented Robust Contextual ASR via COntrastive entity disambiguation (PARCO), which integrates phoneme-aware encoding, contrastive entity disambiguation, entity-level supervision, and hierarchical entity filtering. These components enhance phonetic discrimination, ensure complete entity retrieval, and reduce false positives under uncertainty. Experiments show that PARCO achieves CER of 4.22% on Chinese AISHELL-1 and WER of 11.14% on English DATA2 under 1,000 distractors, significantly outperforming baselines. PARCO also demonstrates robust gains on out-of-domain datasets like THCHS-30 and LibriSpeech.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。