کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
559029 | 875039 | 2013 | 16 صفحه PDF | دانلود رایگان |
![عکس صفحه اول مقاله: Acoustic model adaptation using in-domain background models for dysarthric speech recognition Acoustic model adaptation using in-domain background models for dysarthric speech recognition](/preview/png/559029.png)
Speech production errors characteristic of dysarthria are chiefly responsible for the low accuracy of automatic speech recognition (ASR) when used by people diagnosed with it. A person with dysarthria produces speech in a rather reduced acoustic working space, causing typical measures of speech acoustics to have values in ranges very different from those characterizing unimpaired speech. It is unlikely then that models trained on unimpaired speech will be able to adjust to this mismatch when acted on by one of the currently well-studied adaptation algorithms (which make no attempt to address this extent of mismatch in population characteristics).In this work, we propose an interpolation-based technique for obtaining a prior acoustic model from one trained on unimpaired speech, before adapting it to the dysarthric talker. The method computes a ‘background’ model of the dysarthric talker's general speech characteristics and uses it to obtain a more suitable prior model for adaptation (compared to the speaker-independent model trained on unimpaired speech). The approach is tested with a corpus of dysarthric speech acquired by our research group, on speech of sixteen talkers with varying levels of dysarthria severity (as quantified by their intelligibility). This interpolation technique is tested in conjunction with the well-known maximum a posteriori (MAP) adaptation algorithm, and yields improvements of up to 8% absolute and up to 40% relative, over the standard MAP adapted baseline.
► We propose and investigate an additional step in the acoustic model adaptation process, to separately model ‘normal’ and pathology-induced variations in speech characteristics.
► We do so by trying to account for a recently proposed view of the acoustics of motor speech disorders in the clinical research community.
► This technique is tested in conjunction with MAP adaptation algorithm, and yields improvements of up to 8% absolute and up to 40% relative, over the standard MAP adapted baseline.
Journal: Computer Speech & Language - Volume 27, Issue 6, September 2013, Pages 1147–1162