Sequence labeling to detect stuttering events in read speech
| Autor: | Sadeen Alharbi, Madina Hasan, Phil D. Green, Shelagh Brumfitt, Anthony J. H. Simons |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Feature engineering
Conditional random field Stuttering Computer science media_common.quotation_subject Speech recognition 020206 networking & telecommunications 02 engineering and technology 01 natural sciences Sequence labeling Session (web analytics) Theoretical Computer Science Human-Computer Interaction Reading (process) 0103 physical sciences Classifier (linguistics) 0202 electrical engineering electronic engineering information engineering medicine Speech disorder medicine.symptom 010301 acoustics Software media_common |
| ISSN: | 0885-2308 |
| Popis: | Stuttering is a speech disorder that, if treated during childhood, may be prevented from persisting into adolescence. A clinician must first determine the severity of stuttering, assessing a child during a conversational or reading task, recording each instance of disfluency, either in real time, or after transcribing the recorded session and analysing the transcript. The current study evaluates the ability of two machine learning approaches, namely conditional random fields (CRF) and bi-directional long-short-term memory (BLSTM), to detect stuttering events in transcriptions of stuttering speech. The two approaches are compared for their performance both on ideal hand-transcribed data and also on the output of automatic speech recognition (ASR). We also study the effect of data augmentation to improve performance. A corpus of 35 speakers’ read speech (13K words) was supplemented with a corpus of 63 speakers’ spontaneous speech (11K words) and an artificially-generated corpus (50K words). Experimental results show that, without feature engineering, BLSTM classifiers outperform CRF classifiers by 33.6%. However, adding features to support the CRF classifier yields performance improvements of 45% and 18% over the CRF baseline and BLSTM results, respectively. Moreover, adding more data to train the CRF and BLSTM classifiers consistently improves the results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect