使用韵律和错误启动的数据增强来识别非母语儿童的语音
Data augmentation using prosody and false starts to recognize non-native children's speech
摘要：
本文介绍了AaltoASR的语音识别系统，用于INTERSPEECH 2020共享任务，即针对非母语儿童语音的自动语音识别（ASR）。该任务是从不同年龄组的儿童中识别出有限数量的非母语语音。此外，语音是自发的，有错误的开始转录为部分单词，这在测试转录导致看不见的部分单词。为了应对这两个挑战，我们研究了一种基于数据增强的方法。首先，我们应用基于韵律的数据增强来补充音频数据。其次，我们通过在语言建模语料库中引入部分词噪声来模拟错误启动。在基于韵律的增强数据上训练的声学模型优于使用基线配方或基于SpecAugment的增强的模型。部分词噪声也有助于改进基线语言模型。我们的ASR系统，这些方案的组合，是在评估期内排名第三，并实现了18.71%的字错误率。评估后，我们观察到，增加基于韵律的增强数据的量会导致更好的性能。此外，从假设中去除低置信度分数的单词可以带来进一步的收益。这两项改进将ASR错误率降低到17.99%。
英文摘要：
This paper describes AaltoASR's speech recognition system for the INTERSPEECH 2020 shared task on Automatic Speech Recognition (ASR) for non-native children's speech. The task is to recognize non-native speech from children of various age groups given a limited amount of speech. Moreover, the speech being spontaneous has false starts transcribed as partial words, which in the test transcriptions leads to unseen partial words. To cope with these two challenges, we investigate a data augmentation-based approach. Firstly, we apply the prosody-based data augmentation to supplement the audio data. Secondly, we simulate false starts by introducing partial-word noise in the language modeling corpora creating new words. Acoustic models trained on prosody-based augmented data outperform the models using the baseline recipe or the SpecAugment-based augmentation. The partial-word noise also helps to improve the baseline language model. Our ASR system, a combination of these schemes, is placed third in the evaluation period and achieves the word error rate of 18.71%. Post-evaluation period, we observe that increasing the amounts of prosody-based augmented data leads to better performance. Furthermore, removing low-confidence-score words from hypotheses can lead to further gains. These two improvements lower the ASR error rate to 17.99%.
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。
