Adaptation of a Pronunciation Dictionary for Dysarthric Speech Recognition
Adaptation of a Pronunciation Dictionary for Dysarthric Speech Recognition
复制标题
DOI：
10.1109/lifetech53646.2022.9754848
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Yuya Sawa;R. Takashima;T. Takiguchi
中科院分区：
文献类型：
--
作者：
Yuya Sawa;R. Takashima;T. Takiguchi
在自动语音识别系统的一般框架中，在训练和识别过程中都使用发音字典，发音字典是从音素序列到单词的映射表。然而，在构音障碍的语音识别的情况下，这种发音词典并不总是足够的，因为构音障碍的人通常难以以与词典中发音相同的方式发音单词。在本文中，我们调查的发音字典的适应个人构音障碍的人，并评估适应字典使用构音障碍的语音识别任务的有效性。在所提出的方法中，为了找到规则，我们可以用来修改字典，我们分析的音素识别结果中的误识别模式。通过遵循提取的规则，我们为目标构音障碍者将发音添加到字典中。我们评估的有效性，适应发音字典上的连续语音识别任务，并表明，适应字典可以降低单词错误率。
In the general framework of an automatic speech recognition system, a pronunciation dictionary, that is a mapping table from a phoneme sequence to a word, is used both in the processes of training and recognition. However, this pronunciation dictionary is not always adequate in the case of dysarthric speech recognition because dysarthric people often have difficulty pronouncing words in the same way they are pronounced in the dictionary. In this paper, we investigate the adaptation of a pronunciation dictionary to an individual dysarthric person and evaluate the effectiveness of adapting the dictionary using a dysarthric speech recognition task. In the proposed method, in order to find rules we can use to modify a dictionary, we analyze the pattern of mis-recognition in the phoneme recognition results. By following the extracted rules, we add pronunciations to the dictionary for the target dysarthric person. We evaluate the effectiveness of the adapted pronunciation dictionary on a continuous speech recognition task and demonstrate that the adapted dictionary can decrease the word error rate.