Use of myoelectric signals to recognize speech

Morse, Michael S.; Day, Steven; Trull, B.; Morse, Hanaa F.

doi:10.1109/iembs.1989.96459

Cited by 22 publications

(15 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, for vocabularies over 10 words, the recognition accuracy remained below 70% [254,257] until 2001 when Chan et al [253] achieved classification accuracies of 97% and 90% for two subjects on a 10-word vocabulary of English digits. They used five pairs of gel Ag/AgCl electrodes to measure sEMG signals from five facial muscles: levator anguli oris, zygomaticus major platysma, depressor anguli oris and anterior belly of the digastric.…”

Section: Silent Speech Recognitionmentioning

confidence: 97%

“…The first publications about the sEMG-based speech recognition appeared already in the mid 1980s [39,254]. However, for vocabularies over 10 words, the recognition accuracy remained below 70% [254,257] until 2001 when Chan et al [253] achieved classification accuracies of 97% and 90% for two subjects on a 10-word vocabulary of English digits.…”

Section: Silent Speech Recognitionmentioning

confidence: 98%

“…Silent speech interface (SSI) has shown promise to overcome conventional speech recognition in acoustically harsh environments or in situations where private communication is desired [28,38,39,168,[253][254][255][256]. SSI captures silent speech by analyzing sEMG signals measured on the skin surface around the region of articulatory muscles in the face and neck.…”

Section: Silent Speech Recognitionmentioning

confidence: 99%

See 2 more Smart Citations

Current state of digital signal processing in myoelectric interfaces and related applications

Hakonen

Piitulainen

Visala

2015

Biomedical Signal Processing and Control

257

185

View full text Add to dashboard Cite

a b s t r a c tThis review discusses the critical issues and recommended practices from the perspective of myoelectric interfaces. The major benefits and challenges of myoelectric interfaces are evaluated. The article aims to fill gaps left by previous reviews and identify avenues for future research. Recommendations are given, for example, for electrode placement, sampling rate, segmentation, and classifiers. Four groups of applications where myoelectric interfaces have been adopted are identified: assistive technology, rehabilitation technology, input devices, and silent speech interfaces. The state-of-the-art applications in each of these groups are presented.

show abstract

Section: Silent Speech Recognitionmentioning

confidence: 97%

Section: Silent Speech Recognitionmentioning

confidence: 98%

Section: Silent Speech Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Current state of digital signal processing in myoelectric interfaces and related applications

Hakonen

Piitulainen

Visala

2015

Biomedical Signal Processing and Control

257

185

View full text Add to dashboard Cite

show abstract

“…In later work in 1991, Morse et al applied a neural network to a similar data set and achieved roughly the same correct classification rate of 60%. Other papers from this group include (Morse et al, 1989(Morse et al, , 1990.…”

Section: Background and Related Researchmentioning

confidence: 97%

Small-vocabulary speech recognition using surface electromyography

Betts¹,

Binsted²,

Jorgensen³

2006

Interacting with Computers

View full text Add to dashboard Cite

We present results of electromyographic (EMG) speech recognition on a small vocabulary of 15 English words. EMG speech recognition holds promise for mitigating the effects of high acoustic noise on speech intelligibility in communication systems, including those used by first responders (a focus of this work). We collected 150 examples per word of single-channel EMG data from a male subject, speaking normally while wearing a firefighter's self-contained breathing apparatus. The signal processing consisted of an activity detector, a feature extractor, and a neural network classifier. Testing produced an overall average correct classification rate on the 15 words of 74% with a 95% confidence interval of (71%, 77%). Once trained, the subject used a classifier as part of a real-time system to communicate to a cellular phone and to control a robotic device. These tasks were performed under an ambient noise level of approximately 95 decibels. We also describe ongoing work on phoneme-level EMG speech recognition. Crown

show abstract

“…Due to the noisy environment in such aircraft, conventional speech recognition is limited. Although much research has been done to improve acoustic results under noisy conditions [1][2][3], it is beneficial to consider alternate approaches.…”

Section: Introductionmentioning

confidence: 99%

Performance analysis of wavelet transform for unspoken words

Saini

Neeraj³

2013

2013 International Conference on Signal Processing and Communication (Icsc)

View full text Add to dashboard Cite

This paper aims to identifY unspoken words using fa cial muscle activity without audible signal. A novel approach of wavelet analysis using diff erent filter coefficients and the performance analysis of each filter coefficients along with classifiers is introduced. The technique is successfu lly used to classifY 5 vowels, month name, weekdays and is not sensitive to the variation in sp eed and the sp eaking style of the diff erent subjects and is used as recognition variables to recognize the unspoken words. Th is is an eff icient technique that measures the relative muscle activity of the articulatory fa cial muscles and it is shown that fo rmer systems go through austere performance degradation when new words are acquainted. Us ing wavelet, word error rate and classification rate achieve a noteworthy success. This paper presents wavelet analysis of surfa ce electromyogram (SEMG) of fo ur fa cial muscles to decompose the signal and identifY the words and classifying these words by three wavelets. Us ing three filter coefficients of Daubechies, Coiflets and Sy mlets, the unspoken word has been recognized. Th is represents the proportional muscle activity of the fo ur muscles. These are classified using k-nearest neighbor, probabilistic neural network and support vector machine to identifY the sp eech. It is urged that such applied science may be used fo r the user to give simple voiceless commands when conditioned fo r the sp ecific user.

show abstract

Use of myoelectric signals to recognize speech

Cited by 22 publications

References 4 publications

Current state of digital signal processing in myoelectric interfaces and related applications

Current state of digital signal processing in myoelectric interfaces and related applications

Small-vocabulary speech recognition using surface electromyography

Performance analysis of wavelet transform for unspoken words

Contact Info

Product

Resources

About