Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2023 24th International Conference on Digital Signal Processing |
| Untertitel | DSP |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (elektronisch) | 9798350339598 |
| ISBN (Print) | 979-8-3503-3960-4 |
| Publikationsstatus | Veröffentlicht - 2023 |
| Veranstaltung | 24th International Conference on Digital Signal Processing, DSP 2023 - Rhodes, Griechenland Dauer: 11 Juni 2023 → 13 Juni 2023 |
Publikationsreihe
| Name | International Conference on Digital Signal Processing, DSP |
|---|---|
| Band | 2023-June |
| ISSN (Print) | 1546-1874 |
| ISSN (elektronisch) | 2165-3577 |
Abstract
Cochlear Implants (CIs) are surgically implanted hearing devices that allow to restore a sense of hearing in people suffering from moderate to profound hearing loss. Modern CIs offer wireless streaming of audio to the signal processor of the CI to improve speech understanding in complex acoustic environments. To conserve energy in this wireless streaming, proprietary source coding of the stimulation patterns of CIs was proposed, achieving state-of-the-art results with respect to bitrate, latency and intelligibility of the coded stimulation patterns. This work investigates vector-quantized feedback recurrent autoencoders (VQ FRAE) to improve source coding of the stimulation patterns of CIs. The VQ FRAE is optimized with respect to the non-differentiable STOI using simultaneous perturbation stochastic approximation. With this approach, a state-of-the-art bitrate of 4.69 kbit/s was achieved, while maintaining zero latency and little to no degredation of intelligibility. The FRAE outperforms audio codecs like Opus with respect to bitrate, intelligibility and latency.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Signalverarbeitung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2023 24th International Conference on Digital Signal Processing: DSP. Institute of Electrical and Electronics Engineers Inc., 2023. (International Conference on Digital Signal Processing, DSP; Band 2023-June).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Vector-Quantized Feedback Recurrent Autoencoders for the Compression of the Stimulation Patterns of Cochlear Implants at Zero Delay
AU - Hinrichs, Reemt
AU - Bilsky, Julian
AU - Ostermann, Jorn
PY - 2023
Y1 - 2023
N2 - Cochlear Implants (CIs) are surgically implanted hearing devices that allow to restore a sense of hearing in people suffering from moderate to profound hearing loss. Modern CIs offer wireless streaming of audio to the signal processor of the CI to improve speech understanding in complex acoustic environments. To conserve energy in this wireless streaming, proprietary source coding of the stimulation patterns of CIs was proposed, achieving state-of-the-art results with respect to bitrate, latency and intelligibility of the coded stimulation patterns. This work investigates vector-quantized feedback recurrent autoencoders (VQ FRAE) to improve source coding of the stimulation patterns of CIs. The VQ FRAE is optimized with respect to the non-differentiable STOI using simultaneous perturbation stochastic approximation. With this approach, a state-of-the-art bitrate of 4.69 kbit/s was achieved, while maintaining zero latency and little to no degredation of intelligibility. The FRAE outperforms audio codecs like Opus with respect to bitrate, intelligibility and latency.
AB - Cochlear Implants (CIs) are surgically implanted hearing devices that allow to restore a sense of hearing in people suffering from moderate to profound hearing loss. Modern CIs offer wireless streaming of audio to the signal processor of the CI to improve speech understanding in complex acoustic environments. To conserve energy in this wireless streaming, proprietary source coding of the stimulation patterns of CIs was proposed, achieving state-of-the-art results with respect to bitrate, latency and intelligibility of the coded stimulation patterns. This work investigates vector-quantized feedback recurrent autoencoders (VQ FRAE) to improve source coding of the stimulation patterns of CIs. The VQ FRAE is optimized with respect to the non-differentiable STOI using simultaneous perturbation stochastic approximation. With this approach, a state-of-the-art bitrate of 4.69 kbit/s was achieved, while maintaining zero latency and little to no degredation of intelligibility. The FRAE outperforms audio codecs like Opus with respect to bitrate, intelligibility and latency.
UR - http://www.scopus.com/inward/record.url?scp=85165429834&partnerID=8YFLogxK
U2 - 10.1109/DSP58604.2023.10167999
DO - 10.1109/DSP58604.2023.10167999
M3 - Conference contribution
AN - SCOPUS:85165429834
SN - 979-8-3503-3960-4
T3 - International Conference on Digital Signal Processing, DSP
BT - 2023 24th International Conference on Digital Signal Processing
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 24th International Conference on Digital Signal Processing, DSP 2023
Y2 - 11 June 2023 through 13 June 2023
ER -