Intelligibility Assessment and Speech Recognizer Word Accuracy Rate Prediction for Dysarthric Speakers in a Factor Analysis Subspace

Abstract

Automated intelligibility assessments can support speech and language therapists in determining the type of dysarthria presented by their clients. Such assessments can also help predict how well a person with dysarthria might cope with a voice interface to assistive technology. Our approach to intelligibility assessment is based on iVectors, a set of measures that capture many aspects of a person's speech, including intelligibility. The major advantage of iVectors is that they compress all acoustic information contained in an utterance into a reduced number of measures, and they are very suitable to be used with simple predictors. We show that intelligibility assessments work best if there is a pre-existing set of words annotated for intelligibility from the speaker to be evaluated, which can be used for training our system. We discuss the implications of our findings for practice. . 2015. Intelligibility assessment and speech recognizer word accuracy rate prediction for dysarthric speakers in a factor analysis subspace.

Automatic Assessment of Prosodic Quality in Down Syndrome: Analysis of the Impact of Speaker Heterogeneity

“…Some works focus on the speech intelligibility of people with aphasia [23,24] or speech intelligibility in pathological voices [25,26]. Others try to identify speech disorders in children with cleft lip and palate [27] or to predict automatically some dysarthric speech evaluation metrics, such as intelligibility, severity and articulation impairment [28,29]. In addition, the recognition of speech emotions and autism spectrum disorders has also been investigated [30].…”

Automatic Evaluation of Speech Intelligibility Based on I-vectors in the Context of Head and Neck Cancers

“…In [12], the i-vector paradigm was used as a speaker normalization and involved in a more complex classification approach, combining acoustic and articulatory features for the automatic detection of Amyotrophic Lateral Sclerosis (ALS). In [13], i-vectors were used for the representation of word segments produced by 15 dysarthric speakers resulting in some important correlations between automatically predicted and reference intelligibility measures. Finally, in [14], the authors proposed an approach based on a cosine distance between the i-vector representation of a speech production (test) and two reference i-vectors representing each normal and dysarthric speech.…”

Improving Generalisation to New Speakers in Spoken Dialogue State Tracking

“…For each speaker s, xs is a 50 dimensional vector corresponding to the mean iVector extracted from each utterance from that speaker. For more information on the iVector extraction, refer to [34].…”