Detecting Stuttering Events in Transcripts of Children’s Speech

Alharbi, Sadeen; Hasan, Madina; Simons, Anthony J. H.; Brumfitt, Shelagh; Green, Phil

doi:10.1007/978-3-319-68456-7_18

Cited by 14 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The annotation approach followed in this study is the same approach followed in our previous work [25] and it is the one proposed by Yairi and Ambrose [26]. In this study, all types of stuttering were considered except the interjection and block types.…”

Section: Data Transcription and Annotationmentioning

confidence: 99%

A Lightly Supervised Approach to Detect Stuttering in Children's Speech

et al. 2018

Self Cite

View full text Add to dashboard Cite

In speech pathology, new assistive technologies using ASR and machine learning approaches are being developed for detecting speech disorder events. Classically-trained ASR model tends to remove disfluencies from spoken utterances, due to its focus on producing clean and readable text output. However, diagnostic systems need to be able to track speech disfluencies, such as stuttering events, in order to determine the severity level of stuttering. To achieve this, ASR systems must be adapted to recognise full verbatim utterances, including pseudo-words and non-meaningful part-words. This work proposes a training regime to address this problem, and preserve a full verbatim output of stuttering speech. We use a lightly-supervised approach using task-oriented lattices to recognise the stuttering speech of children performing a standard reading task. This approach improved the WER by 27.8% relative to a baseline that uses word-lattices generated from the original prompt. The improved results preserved 63% of stuttering events (including sound, word, part-word and phrase repetition, and revision). This work also proposes a separate correction layer on top of the ASR that detects prolongation events (which are poorly recognised by the ASR). This increases the percentage of preserved stuttering events to 70%.

show abstract

Section: Data Transcription and Annotationmentioning

confidence: 99%

A Lightly Supervised Approach to Detect Stuttering in Children's Speech

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…HELM and CRF are sequence labelling classifiers, since the probabilistic rules learned by these classifiers are entirely data-driven. Experimental results show that the CRF classifier outperforms the HELM classifier by 2.2% [22]. Our present study demonstrates an evaluation of two machine-learning approaches, CRF and BLSTM for detecting stuttering events both in human and ASR transcripts of children's read speech.…”

Section: Previous Workmentioning

confidence: 75%

“…However, this approach depends on the expert's knowledge being complete, the rules fully covering every possible stuttering event, and articulation of the rules supporting diagnosis without rule-conflicts [21]. Previously [22], we proposed using a probabilistic approach that applies the machine learning classifiers HELM (Hidden Event Language Model) and CRF (Conditional Random Field) to the task of detecting stuttering in transcriptions of continuous children's speech. HELM and CRF are sequence labelling classifiers, since the probabilistic rules learned by these classifiers are entirely data-driven.…”

Section: Previous Workmentioning

confidence: 99%

Sequence labeling to detect stuttering events in read speech

Alharbi

Hasan

Simons

et al. 2020

Computer Speech & Language

Self Cite

View full text Add to dashboard Cite

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

show abstract

“…An alternative strategy of stuttering detection is to apply ASR on the audio speech signal to get the spoken texts and then to use language models [4]- [6]. Even though this method of detecting stuttering has achieved encouraging results and has been proven effective, the reliance on ASR makes it computationally expensive and prone to error.…”

Section: Introductionmentioning

confidence: 99%

StutterNet: Stuttering Detection Using Time Delay Neural Network

Sheikh¹,

Sahidullah²,

Hirsch³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper introduce StutterNet, a novel deep learning based stuttering detection capable of detecting and identifying various types of disfluencies. Most of the existing work in this domain uses automatic speech recognition (ASR) combined with language models for stuttering detection. Compared to the existing work, which depends on the ASR module, our method relies solely on the acoustic signal. We use a time-delay neural network (TDNN) suitable for capturing contextual aspects of the disfluent utterances. We evaluate our system on the UCLASS stuttering dataset consisting of more than 100 speakers. Our method achieves promising results and outperforms the state-ofthe-art residual neural network based method. The number of trainable parameters of the proposed method is also substantially less due to the parameter sharing scheme of TDNN.

show abstract

Detecting Stuttering Events in Transcripts of Children’s Speech

Cited by 14 publications

References 16 publications

A Lightly Supervised Approach to Detect Stuttering in Children's Speech

A Lightly Supervised Approach to Detect Stuttering in Children's Speech

Sequence labeling to detect stuttering events in read speech

StutterNet: Stuttering Detection Using Time Delay Neural Network

Contact Info

Product

Resources

About