Speech Intelligibility for Cochlear Implant Users with the MMSE Noise-Reduction Time-Frequency Mask

Mourão, Gustavo Leão; Costa, Márcio Holsbach; Paul, Stephan

doi:10.1016/j.bspc.2020.101982

Cited by 14 publications

(10 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These two intrusive approaches estimate the perceived intelligibility using both a reference speech in quiet and a processed version of the speech. STOI has a high correlation with speech intelligibility and has been used in CI studies on speech enhancement and sound coding strategies [24], [27], [28], [45], [64], [74]- [78]. NCM is another frequently used indicator for evaluating speech comprehension in CI sound processing [24], [28], [64], [74], [78].…”

Section: G Objective Speech Intelligibilitymentioning

confidence: 99%

“…STOI has a high correlation with speech intelligibility and has been used in CI studies on speech enhancement and sound coding strategies [24], [27], [28], [45], [64], [74]- [78]. NCM is another frequently used indicator for evaluating speech comprehension in CI sound processing [24], [28], [64], [74], [78]. It has been demonstrated that NCM is a reliable predictor for non-tonal languages as well as tonal languages, such as Mandarin [67].…”

Section: G Objective Speech Intelligibilitymentioning

confidence: 99%

See 1 more Smart Citation

ElectrodeNet – A Deep Learning Based Sound Coding Strategy for Cochlear Implants

Huang¹,

Chao²,

Yu³

et al. 2023

Preprint

View full text Add to dashboard Cite

<div> <div> <div> <div> <p>Objective: ElectrodeNet, a deep-learning based sound coding strategy for the cochlear implant (CI), is proposed in this study. The performance between ElectrodeNet and the advanced combination encoder (ACE) coding strategy in speech intelligibility is compared. Methods: ElectrodeNet emulates the ACE strategy and replaces the conventional envelope detection using various forms of artificial neural networks. Network models of deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) were trained using the fast Fourier transformed clean speech and the corresponding electrode stimulation patterns. Objective speech intelligibility was estimated for ElectrodeNets for the factors of loss function, network architecture, language, and noise type. Subjective listening tests for vocoded Mandarin speech were conducted with 40 normal-hearing listeners. Results: DNN, CNN, and LSTM based ElectrodeNets exhibited strong correlations with the ACE strategy in short-time objective intelligibility (STOI) and normalized covariance metric (NCM) scores. For objective evaluations, small mean squared error (MSE) scores between ACE and ElectrodeNets were less than 0.01 under all experimental conditions, whereas linear correlation coefficient (LCC) and Spearman’s rank correlation coefficient (SRCC) were obtained in large values greater than 0.97 and 0.96, respectively. According to the listening test results, substantial positive relationships were also observed between ACE and both DNN and CNN based ElectrodeNets with MSEs smaller than 0.02, and LCCs and SRCCs greater than 0.9. Significance: This study demonstrates the feasibility of using deep learning to encode sound into meaningful patterns for CI listening. </p> </div> </div> </div> </div>

show abstract

Section: G Objective Speech Intelligibilitymentioning

confidence: 99%

Section: G Objective Speech Intelligibilitymentioning

confidence: 99%

ElectrodeNet – A Deep Learning Based Sound Coding Strategy for Cochlear Implants

Huang¹,

Chao²,

Yu³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Among these predictors, STOI and NCM are two intrusive approaches which can effectively estimating speech intelligibility from a reference speech and a processed version of the speech. STOI has a high correlation with speech intelligibility and has been used in CI studies on speech enhancement and sound coding strategies [22], [25], [26], [41], [63], [65]- [69]. NCM is another frequently used indicator for evaluating speech comprehension in CI sound processing [22], [26], [63], [65], [69], including for vocoded Mandarin speech [61].…”

Section: Objective Evaluationmentioning

confidence: 99%

ElectrodeNet – A Deep Learning Based Sound Coding Strategy for Cochlear Implants

Huang¹,

Chao²,

Yu³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>ElectrodeNet, a deep-learning based sound coding strategy for the cochlear implant (CI), is proposed in this study. </p> <p>ElectrodeNet emulates the ACE strategy by replacing the conventional envelope detection using various artificial neural networks, and the extended ElectrodeNet-CS strategy further incorporates the channel selection (CS) in the network. Network models of deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) were trained using the Fast Fourier Transformed bins and electrode stimulation patterns from the processing of the ACE strategy for clean speech. Objective speech understanding using short-time objective intelligibility (STOI) and normalized covariance metric (NCM) was estimated for ElectrodeNet with the factors of network architecture, dataset language, and noise type using CI simulations. Subjective listening tests for vocoded Mandarin speech were conducted with normal-hearing listeners to measure sentence recognition scores. DNN, CNN, and LSTM based ElectrodeNets exhibited strong correlations to ACE in objective and subjective scores using mean squared error (MSE), linear correlation coefficient (LCC) and Spearman’s rank correlation coefficient (SRCC). The ElectrodeNet-CS strategy was capable of producing N-of-M compatible electrode patterns using a modified DNN network to embed maxima selection, and to perform in similar or even slightly above average in STOI and sentence recognition compared to ACE. The methods and findings in this study demonstrated the feasibility and potential of using deep learning in CI sound coding strategy.</p>

show abstract

“…Foram utilizados os seguintes parâmetros: min = 0,0318 (−15 dB) e a = 0,98 [21]. A densidade espectral de potência do ruído é estimada usando o método de estatísticas regionais [21] [22].…”

Section: Máscara C2funclassified

Redução de Ruído em Implantes Cocleares utilizando uma Rede Neural Recorrente baseada na Estimação da Envoltória da Fala

Gubert¹,

Costa²

2021

Anais Do XXXIX Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

Resumo-Este trabalho apresenta um método de redução de ruído para implantes cocleares baseado em uma rede neural recorrente. O aprendizado é realizado a partir de estimativas da potência da fala contaminada e de uma máscara tempo-frequência ideal, que tem como objetivo a estimação da envoltória da fala. Simulações computacionais usando um critério objetivo indicam aumento significativo de inteligibilidade em comparação à implementação prática (usando um estimador real da razão sinal ruído) da máscara utilizada no treinamento. Os resultados obtidos sugerem que o desempenho da rede neural recorrente se aproxima ao da máscara ideal nas condições analisadas.Palavras-Chave-Implante coclear, redução de ruído, redes neurais.

show abstract

Speech Intelligibility for Cochlear Implant Users with the MMSE Noise-Reduction Time-Frequency Mask

Cited by 14 publications

References 47 publications

ElectrodeNet – A Deep Learning Based Sound Coding Strategy for Cochlear Implants

ElectrodeNet – A Deep Learning Based Sound Coding Strategy for Cochlear Implants

ElectrodeNet – A Deep Learning Based Sound Coding Strategy for Cochlear Implants

Redução de Ruído em Implantes Cocleares utilizando uma Rede Neural Recorrente baseada na Estimação da Envoltória da Fala

Contact Info

Product

Resources

About