Hearing, listening and deep neural networks in hearing aids

Beck, Douglas L.

doi:10.15406/joentr.2021.13.00481

Cited by 4 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advances in calculation speed and energy efficiency, computational complexity is becoming less of a primary issue in hardware design, especially for compressed pre-trained network models on devices. Using the analogy of commercial hearing aids with DNN models [22] and complicated ASR chips [83], the innovation for CI coding strategy is expected to be in a similar transitional process. For hearing assistive devices, latency is another critical challenge, and real-time inference with compact models is an important direction for investigation [49].…”

Section: Discussionmentioning

confidence: 99%

“…In the recent decade, AI based approaches have changed hearing healthcare [11] and various aspects of the 'AI + CI' research [12], including prognosis estimation [13], electrode placement [14], robotic surgery [15], mapping [16], and sound signal processing [17], [18]. In addition, the success of deep learning in general audio processing [19], [20] and hearing aids [21], [22] may also change CI sound processing.…”

mentioning

confidence: 99%

See 1 more Smart Citation

ElectrodeNet—A Deep-Learning-Based Sound Coding Strategy for Cochlear Implants

Huang

Chao

Tsao

2024

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

ElectrodeNet, a deep learning based sound coding strategy for the cochlear implant (CI), is proposed to emulate the advanced combination encoder (ACE) strategy by replacing the conventional envelope detection using various artificial neural networks. The extended ElectrodeNet-CS strategy further incorporates the channel selection (CS). 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 channel envelopes obtained from the processing of clean speech by the ACE strategy. Objective speech understanding using short-time objective intelligibility (STOI) and normalized covariance metric (NCM) was estimated for ElectrodeNet using CI simulations. Sentence recognition tests for vocoded Mandarin speech were conducted with normalhearing listeners. 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 higher average in STOI and sentence recognition compared to ACE. The methods and findings demonstrated the feasibility and potential of using deep learning in CI coding strategy.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

ElectrodeNet—A Deep-Learning-Based Sound Coding Strategy for Cochlear Implants

Huang

Chao

Tsao

2024

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

show abstract

“…With the advances in computation speed and energy efficiency, complexity will not continue to be a primary issue in the hardware design, especially for compressed pre-trained network models on devices. Using the analogy of commercial hearing aids with DNN models [19] and complicated ASR chips [74], the innovation for CI coding strategy is expected to be in a similar transitional process. Latency is critical to hearing assistive devices and real-time inference is another challenge to be overcome using compact models [42].…”

Section: Discussionmentioning

confidence: 99%

“…Machine learning and deep learning have changed various aspects of the 'AI + CI' research [9], including prognosis estimation [10], electrode placement [11], robotic surgery [12], mapping [13], and sound signal processing [14], [15]. In addition, the success of deep learning in general audio processing [16], [17] and hearing aids [18], [19] may also change CI sound processing.…”

Section: Introductionmentioning

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

ElectrodeNet, a deep-learning based sound coding strategy for the cochlear implant (CI), is proposed in this study. 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.

show abstract

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

ElectrodeNet, a deep learning based sound coding strategy for the cochlear implant (CI), is proposed to emulate the advanced combination encoder (ACE) strategy by replacing the conventional envelope detection using various artificial neural networks. The extended ElectrodeNet-CS strategy further incorporates the channel selection (CS). 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 channel envelopes obtained from the processing of clean speech by the ACE strategy. Objective speech understanding using short-time objective intelligibility (STOI) and normalized covariance metric (NCM) was estimated for ElectrodeNet using CI simulations. Sentence recognition tests for vocoded Mandarin speech were conducted with normal-hearing listeners. 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 higher average in STOI and sentence recognition compared to ACE. The methods and findings demonstrated the feasibility and potential of using deep learning in CI coding strategy.

show abstract

Hearing, listening and deep neural networks in hearing aids

Cited by 4 publications

References 16 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

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

Contact Info

Product

Resources

About