PulseAugur
实时 11:05:27
English(EN) COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation

新的COALA框架通过上下文偏置提升语音识别能力

研究人员开发了COALA,一个旨在通过整合外部知识来改进自动语音识别(ASR)系统的新型框架。COALA通过将潜在表示映射到判别空间来增强语音增强语言模型(SLM),从而能够精确量化音频片段与候选实体的匹配程度。该方法解决了SLM上下文窗口的局限性,并解决了多目标发音中的训练崩溃问题,在LibriSpeech基准测试中展示了卓越的上下文偏置性能。 AI

影响 通过整合外部知识提高ASR准确性,可能改进特定领域的应用。

排序理由 该集群包含一篇详细介绍ASR新框架的研究论文。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的COALA框架通过上下文偏置提升语音识别能力

报道来源 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Jhih-Rong Guo, Bi-Cheng Yan, Tien-Hong Lo, Berlin Chen ·

    COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation

    arXiv:2607.08117v1 Announce Type: new Abstract: Contextual biasing seeks to integrate external knowledge into automatic speech recognition (ASR) systems to accurately recognize domain-specific entities. In this paper, we propose COALA (Contextualized ASR Leveraging Biasing Scorin…

  2. arXiv cs.CL TIER_1 English(EN) · Berlin Chen ·

    COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation

    Contextual biasing seeks to integrate external knowledge into automatic speech recognition (ASR) systems to accurately recognize domain-specific entities. In this paper, we propose COALA (Contextualized ASR Leveraging Biasing Scoring), a robust framework designed to enhance speec…