Detection of Consonant Errors in Disordered Speech Based on Consonant-Vowel Segment Embedding

Ng, Si Ioi; Ng, Cymie Wing-Yee; Li, Jingyu; Lee, Tan

doi:10.21437/interspeech.2021-1305

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results are recapitulated for diagnosis of the child. Our proposed approach based on speaker-level representation is compared with methods in which word-level or phone-level error detection is done first on individual test words and subsequently combined to obtain the subject-level decision [11,13,18]. Phone-level detection is implemented based on our previous work in [11].…”

Section: Fusing Phone/word-level Resultsmentioning

confidence: 99%

“…Our proposed approach based on speaker-level representation is compared with methods in which word-level or phone-level error detection is done first on individual test words and subsequently combined to obtain the subject-level decision [11,13,18]. Phone-level detection is implemented based on our previous work in [11]. A DNN model is trained on the classification task to extract fixed-dimension embeddings of consonant-vowel segments.…”

Section: Fusing Phone/word-level Resultsmentioning

confidence: 99%

“…Posterior features were derived from automatic speech recognition systems to facilitate mispronunciation detection in disordered child speech [9,10]. Considering that consonant error could alter the acoustical characteristics of its neighbouring vowel, our recent work proposed to detect consonant errors from consonant-vowel speech segments [11]. The phoneme-level error detection requires automatic time alignment of the target phoneme segments.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Detection of Speech Sound Disorder in Child Speech Using Posterior-based Speaker Representations

Ng¹,

Ng²,

Wang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents a macroscopic approach to automatic detection of speech sound disorder (SSD) in child speech. Typically, SSD is manifested by persistent articulation and phonological errors on specific phonemes in the language. The disorder can be detected by focally analyzing the phonemes or the words elicited by the child subject. In the present study, instead of attempting to detect individual phone-and word-level errors, we propose to extract a subject-level representation from a long utterance that is constructed by concatenating multiple test words. The speaker verification approach, and posterior features generated by deep neural network models, are applied to derive various types of holistic representations. A linear classifier is trained to differentiate disordered speech in normal one. On the task of detecting SSD in Cantonese-speaking children, experimental results show that the proposed approach achieves improved detection performance over previous method that requires fusing phone-level detection results. Using articulatory posterior features to derive i-vectors from multiple-word utterances achieves an unweighted average recall of 78.2% and a macro F1 score of 78.0%.

show abstract