Scholarlink

<p>With the advancement of neural networks, end-to-end neural automatic speech recognition (ASR) systems have demonstrated significant improvements in identifying contextually biased words. However, the incorporation of bias layers introduces additional computational complexity, requires increased resources, and leads to redundant biases. In this paper, we propose a Context Bias Adaptive Model, which dynamically assesses the presence of biased words in the input and applies context biasing accordingly. Consequently, the bias layer is activated only for input audio containing biased words, rather than indiscriminately introducing contextual bias information for every input. Our findings indicate that the Context Bias Adaptive Model effectively mitigates the adverse effects of contextual bias while substantially reducing computational costs.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptive context biasing in transformer-based ASR systems

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月6日

查看全文
  • Nurmemet Yolwas,
  • Yineng Cai,
  • Lixu Sun,
  • Yongchao Li,
  • Wushouer Silamu,
  • Qiqi Du,
  • Ya Huang,
  • Zhiwu Sun,
  • Jian Peng,
  • Yajie Wei

摘要

With the advancement of neural networks, end-to-end neural automatic speech recognition (ASR) systems have demonstrated significant improvements in identifying contextually biased words. However, the incorporation of bias layers introduces additional computational complexity, requires increased resources, and leads to redundant biases. In this paper, we propose a Context Bias Adaptive Model, which dynamically assesses the presence of biased words in the input and applies context biasing accordingly. Consequently, the bias layer is activated only for input audio containing biased words, rather than indiscriminately introducing contextual bias information for every input. Our findings indicate that the Context Bias Adaptive Model effectively mitigates the adverse effects of contextual bias while substantially reducing computational costs.