Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences |
| Untertitel | (IECBES) |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 165-170 |
| Seitenumfang | 6 |
| ISBN (elektronisch) | 9781665494694 |
| ISBN (Print) | 978-1-6654-9470-0 |
| Publikationsstatus | Veröffentlicht - 2022 |
| Veranstaltung | 7th IEEE-EMBS Conference on Biomedical Engineering and Sciences, IECBES 2022 - Virtual, Online, Malaysia Dauer: 7 Dez. 2022 → 9 Dez. 2022 |
Abstract
Cochlear implants (CIs) are battery-powered, surgically implanted hearing-aids capable of restoring a sense of hearing in people suffering from moderate to profound hearing loss. Wireless transmission of audio from or to signal processors of cochlear implants can be used to improve speech understanding and localization of CI users. Data compression algorithms can be used to conserve battery power in this wireless transmission. However, very low latency is a strict requirement, limiting severly the available source coding algorithms. Previously, instead of coding the audio, coding of the electrical stimulation patterns of CIs was proposed to optimize the trade-off between bit-rate, latency and quality. In this work, a zero-delay deep autoencoder (DAE) for the coding of the electrical stimulation patters of CIs is proposed. Combining for the first time bayesian optimization with numerical approximated gradients of a nondifferential speech intelligibility measure for CIs, the short-time intelligibility measure (STOI), an optimized DAE architecture was found and trained that achieved equal or superior speech understanding at zero delay, outperforming well-known audio codecs. The DAE achieved reference vocoder STOI scores at 13.5 kbit/s compared to 33.6 kbit/s for Opus and 24.5 kbit/s for AMR-WB.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Artificial intelligence
- Informatik (insg.)
- Angewandte Informatik
- Informatik (insg.)
- Mensch-Maschine-Interaktion
- Informatik (insg.)
- Signalverarbeitung
- Ingenieurwesen (insg.)
- Biomedizintechnik
- Physik und Astronomie (insg.)
- Instrumentierung
Ziele für nachhaltige Entwicklung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences : (IECBES). Institute of Electrical and Electronics Engineers Inc., 2022. S. 165-170.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Vector-Quantized Zero-Delay Deep Autoencoders for the Compression of Electrical Stimulation Patterns of Cochlear Implants using STOI
AU - Hinrichs, Reemt
AU - Ortmann, Felix
AU - Ostermann, Jorn
N1 - Funding Information: This work was supported by the DFG Cluster of Excellence EXC 1077/1 Hearing4all and funded by the German Research Foundation (DFG) - Project number: 381895691.
PY - 2022
Y1 - 2022
N2 - Cochlear implants (CIs) are battery-powered, surgically implanted hearing-aids capable of restoring a sense of hearing in people suffering from moderate to profound hearing loss. Wireless transmission of audio from or to signal processors of cochlear implants can be used to improve speech understanding and localization of CI users. Data compression algorithms can be used to conserve battery power in this wireless transmission. However, very low latency is a strict requirement, limiting severly the available source coding algorithms. Previously, instead of coding the audio, coding of the electrical stimulation patterns of CIs was proposed to optimize the trade-off between bit-rate, latency and quality. In this work, a zero-delay deep autoencoder (DAE) for the coding of the electrical stimulation patters of CIs is proposed. Combining for the first time bayesian optimization with numerical approximated gradients of a nondifferential speech intelligibility measure for CIs, the short-time intelligibility measure (STOI), an optimized DAE architecture was found and trained that achieved equal or superior speech understanding at zero delay, outperforming well-known audio codecs. The DAE achieved reference vocoder STOI scores at 13.5 kbit/s compared to 33.6 kbit/s for Opus and 24.5 kbit/s for AMR-WB.
AB - Cochlear implants (CIs) are battery-powered, surgically implanted hearing-aids capable of restoring a sense of hearing in people suffering from moderate to profound hearing loss. Wireless transmission of audio from or to signal processors of cochlear implants can be used to improve speech understanding and localization of CI users. Data compression algorithms can be used to conserve battery power in this wireless transmission. However, very low latency is a strict requirement, limiting severly the available source coding algorithms. Previously, instead of coding the audio, coding of the electrical stimulation patterns of CIs was proposed to optimize the trade-off between bit-rate, latency and quality. In this work, a zero-delay deep autoencoder (DAE) for the coding of the electrical stimulation patters of CIs is proposed. Combining for the first time bayesian optimization with numerical approximated gradients of a nondifferential speech intelligibility measure for CIs, the short-time intelligibility measure (STOI), an optimized DAE architecture was found and trained that achieved equal or superior speech understanding at zero delay, outperforming well-known audio codecs. The DAE achieved reference vocoder STOI scores at 13.5 kbit/s compared to 33.6 kbit/s for Opus and 24.5 kbit/s for AMR-WB.
KW - autoencoder
KW - cochlear implants
KW - hyperparameter optimization
KW - Kiefer-Wolfowitz
UR - http://www.scopus.com/inward/record.url?scp=85152382534&partnerID=8YFLogxK
U2 - 10.1109/IECBES54088.2022.10079466
DO - 10.1109/IECBES54088.2022.10079466
M3 - Conference contribution
AN - SCOPUS:85152382534
SN - 978-1-6654-9470-0
SP - 165
EP - 170
BT - 2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th IEEE-EMBS Conference on Biomedical Engineering and Sciences, IECBES 2022
Y2 - 7 December 2022 through 9 December 2022
ER -