Computerized speech recognition: influence of intelligibility and perceptual consistency on recognition accuracy

Thomas‐Stonell, Nancy; Kotler, Ava-Lee; Leeper, Herbert A.; Doyle, Philip C.

doi:10.1080/07434619812331278196

Cited by 40 publications

(16 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early research investigating the performance of ASR systems on speech from speakers with different degrees of dysarthria, e.g., suffering from Friedrichs Ataxia [9,10], traumatic brain injury [11,10] and cerebral palsy [11,10], reported in all cases a higher Word Error Rate (WER) on speech from patients than on that of controls. The number of speakers in those studies, however, was rather low, i.e., below 7 while the present study scales up the number of speakers with PD to 43.…”

Section: Related Workmentioning

confidence: 99%

Study of the Performance of Automatic Speech Recognition Systems in Speakers with Parkinson’s Disease

Moro-Velázquez¹,

Cho²,

Watanabe³

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

Parkinson's Disease (PD) affects motor capabilities of patients, who in some cases need to use human-computer assistive technologies to regain independence. The objective of this work is to study in detail the differences in error patterns from stateof-the-art Automatic Speech Recognition (ASR) systems on speech from people with and without PD. Two different speech recognizers (attention-based end-to-end and Deep Neural Network-Hidden Markov Models hybrid systems) were trained on a Spanish language corpus and subsequently tested on speech from 43 speakers with PD and 46 without PD. The differences related to error rates, substitutions, insertions and deletions of characters and phonetic units between the two groups were analyzed, showing that the word error rate is 27% higher in speakers with PD than in control speakers, with a moderated correlation between that rate and the developmental stage of the disease. The errors were related to all manner classes, and were more pronounced in the vowel /u/. This study is the first to evaluate ASR systems' responses to speech from patients at different stages of PD in Spanish. The analyses showed general trends but individual speech deficits must be studied in the future when designing new ASR systems for this population.

show abstract

Section: Related Workmentioning

confidence: 99%

Study of the Performance of Automatic Speech Recognition Systems in Speakers with Parkinson’s Disease

Moro-Velázquez¹,

Cho²,

Watanabe³

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

show abstract

“…However it is important to develop ASR systems for dysarthric speakers because of the advantages they offer when compared with interfaces such as switches or keyboards. These may be more physically demanding and tiring [14][15][16][17] and as dysarthria is usually accompanied by other physical handicaps, impossible for them to use. Even with the speech production difficulties exhibited by many of these speakers, speech communication requires less effort and is faster than conventional typing methods [18], despite the difficulty of achieving robust recognition performance.…”

Section: Introductionmentioning

confidence: 99%

Modelling Errors in Automatic Speech Recognition for Dysarthric Speakers

Morales

Cox

2009

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Dysarthria is a motor speech disorder characterized by weakness, paralysis, or poor coordination of the muscles responsible for speech. Although automatic speech recognition (ASR) systems have been developed for disordered speech, factors such as low intelligibility and limited phonemic repertoire decrease speech recognition accuracy, making conventional speaker adaptation algorithms perform poorly on dysarthric speakers. In this work, rather than adapting the acoustic models, we model the errors made by the speaker and attempt to correct them. For this task, two techniques have been developed: (1) a set of "metamodels" that incorporate a model of the speaker's phonetic confusion matrix into the ASR process; (2) a cascade of weighted finite-state transducers at the confusion matrix, word, and language levels. Both techniques attempt to correct the errors made at the phonetic level and make use of a language model to find the best estimate of the correct word sequence. Our experiments show that both techniques outperform standard adaptation techniques.

show abstract

“…Commercially available automatic speech recognition (ASR) systems can work well for some people with mild and even moderate dysarthria [7] and [8], but these studies show that there is an inverse relationship between the degree of impairment and the accuracy of speech recognition. For people with severe speech impairment, commercial speech recognition systems are not a viable access solution.…”

mentioning

confidence: 99%

“…For people with severe speech impairment, commercial speech recognition systems are not a viable access solution. Moreover, the small-scale laboratory experiments reported in [7], [8] do not represent the range of environmental conditions that are likely to be encountered in realistic usage, which is known to degrade recognition accuracy.…”

mentioning

confidence: 99%

A Voice-Input Voice-Output Communication Aid for People With Severe Speech Impairment

Hawley

Cunningham

Green

et al. 2013

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

A new form of augmentative and alternative communication (AAC) device for people with severe speech impairment-the voice-input voice-output communication aid (VIVOCA)-is described. The VIVOCA recognizes the disordered speech of the user and builds messages, which are converted into synthetic speech. System development was carried out employing user-centered design and development methods, which identified and refined key requirements for the device. A novel methodology for building small vocabulary, speaker-dependent automatic speech recognizers with reduced amounts of training data, was applied. Experiments showed that this method is successful in generating good recognition performance (mean accuracy 96%) on highly disordered speech, even when recognition perplexity is increased. The selected message-building technique traded off various factors including speed of message construction and range of available message outputs. The VIVOCA was evaluated in a field trial by individuals with moderate to severe dysarthria and confirmed that they can make use of the device to produce intelligible speech output from disordered speech input. The trial highlighted some issues which limit the performance and usability of the device when applied in real usage situations, with mean recognition accuracy of 67% in these circumstances. These limitations will be addressed in future work.

show abstract

Computerized speech recognition: influence of intelligibility and perceptual consistency on recognition accuracy

Cited by 40 publications

References 6 publications

Study of the Performance of Automatic Speech Recognition Systems in Speakers with Parkinson’s Disease

Study of the Performance of Automatic Speech Recognition Systems in Speakers with Parkinson’s Disease

Modelling Errors in Automatic Speech Recognition for Dysarthric Speakers

A Voice-Input Voice-Output Communication Aid for People With Severe Speech Impairment

Contact Info

Product

Resources

About