The optimal electromyography feature for oral muscle movements

Pothirat, Tammarot; Chatpun, Surapong; Phukpattaranont, Pornchai; vongjandaeng, Duangmon

doi:10.1109/bmeicon.2013.6687639

Cited by 4 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3. It is superior to previous results from the unimodal fusion, such as accuracy at 91% and 94% for classification of five oral activities from six sEMG channels [14] and classification of nine Thai syllables from five sEMG channels [15], respectively. In [13], the multimodal fusion between one acoustic signal and five sEMG channels is used to classify ten words based on phonemes.…”

Section: Discussioncontrasting

confidence: 56%

“…Features used in recognition of sEMG signals from the facial muscles can be determined based on their amplitude values, frequency contents, and statistical values. The popular amplitude based features include root-mean-squared value [11]- [14], mean absolute value, zero crossing [11], [14], [15], waveform length [14], [15], and slope sign change [14]. While frequency based features commonly extracted are Fast Fourier transform coefficients [11] and mean frequency [15], statistical based features are kurtosis [11], [15] and skewness [15].…”

Section: B Feature Extractionmentioning

confidence: 99%

“…Speech recognition systems have been developed in other languages [11]- [13] but there is limited literature available for the Thai language. Pothirat et al [14] classified five oral movement activities used to improve oral motor for speech production using six channels of sEMG signals recorded from the face and the neck. The average classification accuracy achieved was 91.3%.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multimodal Data Fusion of Electromyography and Acoustic Signals for Thai Syllable Recognition

Jong

Herrera

Phukpattaranont

2021

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

Speech disorders such as dysarthria are common and frequent after suffering a stroke. Speech rehabilitation performed by a speech-language pathologist is needed to improve and recover. However, in Thailand, there is a shortage of speech-language pathologists. In this paper, we present a syllable recognition system, which can be deployable in a speech rehabilitation system to provide support to the limited speech-language pathologists available. The proposed system is based on a multimodal fusion of acoustic signal and surface electromyography (sEMG) collected from facial muscles. Multimodal data fusion is studied to improve signal collection under noisy situations while reducing the number of electrodes needed. The signals are simultaneously collected while articulating 12 Thai syllables designed for rehabilitation exercises. Several features are extracted from sEMG signals and five channels are studied. The best combination of features and channels is chosen to be fused with the mel-frequency cepstral coefficients extracted from the acoustic signal. The feature vector from each signal source is projected by spectral regression extreme learning machine and concatenated. Data from seven healthy subjects were collected for evaluation purposes. Results show that the multimodal fusion outperforms the use of a single signal source achieving up to ∼ 98% of accuracy. In other words, an accuracy improvement up to 5% can be achieved when using the proposed multimodal fusion. Moreover, its low standard deviations in classification accuracy compared to those from the unimodal fusion indicate the improvement in the robustness of the syllable recognition.

show abstract

Section: Discussioncontrasting

confidence: 56%

Section: B Feature Extractionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multimodal Data Fusion of Electromyography and Acoustic Signals for Thai Syllable Recognition

Jong

Herrera

Phukpattaranont

2021

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In fact, the obtained results show that this system can recognize laughter from other different actions with a global correct discrimination rate of at least 64%. These results, especially the ones obtained with the binary classifiers, compared with previous works in the field, using acoustic features [14]- [22], or other sEMG-based system s, [36], [44]- [49], are not particularly impressive. However, even if this EMG-based system is more invasive compared to video or audio systems, it is less invasive compared to previously developed sEMG systems, and it could be used either as standalone wearable system or as an auxiliary system to detect and classify laughter together with audio or video systems.…”

Section: Discussionmentioning

confidence: 54%

Automatic discrimination of laughter using distributed sEMG

Cosentino

Sessa

Kong

et al. 2015

2015 International Conference on Affective Computing and Intelligent Interaction (ACII)

View full text Add to dashboard Cite

Laughter is a very interesting non-verbal human vocalization. It is classified as a semi voluntary behavior despite being a direct form of social interaction, and can be elicited by a variety of very different stimuli, both cognitive and physical. Automatic laughter detection, analysis and classification will boost progress in affective computing, leading to the development of more natural human-machine communication interfaces. Surface Electromyography (sEMG) on abdominal muscles or invasive EMG on the larynx show potential in this direction, but these kinds of EMG-based sensing systems cannot be used in ecological settings due to their size, lack of reusability and uncomfortable setup. For this reason, they cannot be easily used for natural detection and measurement of a volatile social behavior like laughter in a variety of different situations. We propose the use of miniaturized, wireless, dry-electrode sEMG sensors on the neck for the detection and analysis of laughter. Even if with this solution the activation of specific larynx muscles cannot be precisely measured, it is possible to detect different EMG patterns related to larynx function. In addition, integrating sEMG analysis on a multisensory compact system positioned on the neck would improve the overall robustness of the whole sensing system, enabling the synchronized measure of different characteristics of laughter, like vocal production, head movement or facial expression; being at the same time less intrusive, as the neck is normally more accessible than abdominal muscles. In this paper, we report laughter discrimination rate obtained with our system depending on different conditions.

show abstract