arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.01677cs.CL
收藏

快速鲁棒的语音识别无监督上下文偏置

Fast and Robust Unsupervised Contextual Biasing for Speech Recognition

Salesforce.com, Inc.(赛富时公司)

Young Mo Kang, Yingbo Zhou

摘要:

自动语音识别(ASR)系统正在成为一种普遍存在的技术。虽然它的准确性在某些设置下正在缩小与人类水平的差距,但可以进一步改进的一个领域是纳入用户特定的信息或上下文来使其预测产生偏差。一种常见的框架是从所提供的上下文迷你语料库动态地构建小语言模型,并且在解码过程期间用主语言模型内插其得分。在这里,我们提出了一种替代方法,不需要显式的上下文语言模型。相反,我们从训练语料库中获得系统词汇表中每个单词的偏差分数。该方法的独特之处在于:1)它不需要上下文或训练语料库的元数据或类标签注释。2)偏差分数与单词的对数概率成比例,因此它不仅会使所提供的上下文发生偏差,而且对不相关的上下文(例如,用户错误指定或难以量化严格范围的情况)也是鲁棒的。3)在训练阶段期间预先确定整个词汇表的偏差分数,从而消除了在推理期间计算上昂贵的语言模型构造。当相关上下文可用时,我们在识别准确性方面表现出显着的改进。此外,我们还证明了所提出的方法具有较高的容忍度,在不相关的上下文存在的假触发错误。

英文摘要:

Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area that can further improve is to incorporate user-specific information or context to bias its prediction. A common framework is to dynamically construct a small language model from the provided contextual mini corpus and interpolate its score with the main language model during the decoding process. Here we propose an alternative approach that does not entail explicit contextual language model. Instead, we derive the bias score for every word in the system vocabulary from the training corpus. The method is unique in that 1) it does not require meta-data or class-label annotation for the context or the training corpus. 2) The bias score is proportional to the word's log-probability, thus not only would it bias the provided context, but also robust against irrelevant context (e.g. user mis-specified or in case where it is hard to quantify a tight scope). 3) The bias score for the entire vocabulary is pre-determined during the training stage, thereby eliminating computationally expensive language model construction during inference. We show significant improvement in recognition accuracy when the relevant context is available. Additionally, we also demonstrate that the proposed method exhibits high tolerance to false-triggering errors in the presence of irrelevant context.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑