arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.03327eess.AScs.LG
收藏

端到端语音识别中改进的域外数据置信度估计

Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition

Google(谷歌)

Qiujia Li, Yu Zhang, David Qiu, Yanzhang He, Liangliang Cao, Philip C. Woodland

摘要:

随着端到端自动语音识别(ASR)模型达到有希望的性能,各种下游任务依赖于这些系统的良好置信度估计器。最近的研究表明,基于模型的置信度估计器比使用输出softmax概率具有显着的优势。如果语音识别器的输入数据来自不匹配的声学和语言条件,则ASR性能和相应的置信度估计器可能表现出严重的退化。由于置信度模型通常在与ASR相同的域内数据上进行训练,因此推广到域外(OOD)场景具有挑战性。在保持ASR模型不变的情况下,本文提出了两种改进基于模型的OOD数据置信度估计的方法:使用伪transmittance和一个额外的OOD语言模型。通过在LibriSpeech上训练的ASR模型,实验表明,所提出的方法可以大大提高TED-LIUM和Switchboard数据集上的置信度,同时保持域内性能。此外,改进的置信估计更好地校准OOD数据,可以提供一个更可靠的标准,数据选择。

英文摘要:

As end-to-end automatic speech recognition (ASR) models reach promising performance, various downstream tasks rely on good confidence estimators for these systems. Recent research has shown that model-based confidence estimators have a significant advantage over using the output softmax probabilities. If the input data to the speech recogniser is from mismatched acoustic and linguistic conditions, the ASR performance and the corresponding confidence estimators may exhibit severe degradation. Since confidence models are often trained on the same in-domain data as the ASR, generalising to out-of-domain (OOD) scenarios is challenging. By keeping the ASR model untouched, this paper proposes two approaches to improve the model-based confidence estimators on OOD data: using pseudo transcriptions and an additional OOD language model. With an ASR model trained on LibriSpeech, experiments show that the proposed methods can greatly improve the confidence metrics on TED-LIUM and Switchboard datasets while preserving in-domain performance. Furthermore, the improved confidence estimators are better calibrated on OOD data and can provide a much more reliable criterion for data selection.

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。

↑