DSENet : Directional Signal Extraction Network for Hearing Improvement on Edge Devices
In this paper, we propose a directional signal extraction network (DSENet). DSENet is a low-latency, real-time neural network that, given a reverberant mixture of signals captured by a microphone array, aims at extracting the reverberant signal whose source is located within a directional region of interest. If there are multiple sources situated within the directional region of interest, DSENet will aim at extracting a combination of their reverberant signals. As such, the formulation of DSENet circumvents the well-known crosstalk problem in beamforming while providing an alternative and perhaps more practical approach to other spatially constrained signal extraction methods proposed in the literature. DSENet is based on a computationally efficient and low-distortion linear model formulated in the time domain. As a result, an important application of our work is hearing improvement on edge devices. Simulation results show that DSENet outperforms oracle beamformers, as well as state-of-the-art in low-latency causal speech separation, while incurring a system latency of only 4 ms. Additionally, DSENet has been successfully deployed as a real-time application on a smartphone.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:11 |
---|---|
Enthalten in: |
IEEE access : practical innovations, open solutions - 11(2023) vom: 11., Seite 4350-4358 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Kovalyov, Anton [VerfasserIn] |
---|
Links: |
---|
Themen: |
Beamforming |
---|
Anmerkungen: |
Date Revised 29.08.2023 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.1109/access.2023.3235948 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM361199945 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM361199945 | ||
003 | DE-627 | ||
005 | 20231226084628.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1109/access.2023.3235948 |2 doi | |
028 | 5 | 2 | |a pubmed24n1203.xml |
035 | |a (DE-627)NLM361199945 | ||
035 | |a (NLM)37621739 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Kovalyov, Anton |e verfasserin |4 aut | |
245 | 1 | 0 | |a DSENet |b Directional Signal Extraction Network for Hearing Improvement on Edge Devices |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 29.08.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a In this paper, we propose a directional signal extraction network (DSENet). DSENet is a low-latency, real-time neural network that, given a reverberant mixture of signals captured by a microphone array, aims at extracting the reverberant signal whose source is located within a directional region of interest. If there are multiple sources situated within the directional region of interest, DSENet will aim at extracting a combination of their reverberant signals. As such, the formulation of DSENet circumvents the well-known crosstalk problem in beamforming while providing an alternative and perhaps more practical approach to other spatially constrained signal extraction methods proposed in the literature. DSENet is based on a computationally efficient and low-distortion linear model formulated in the time domain. As a result, an important application of our work is hearing improvement on edge devices. Simulation results show that DSENet outperforms oracle beamformers, as well as state-of-the-art in low-latency causal speech separation, while incurring a system latency of only 4 ms. Additionally, DSENet has been successfully deployed as a real-time application on a smartphone | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Real-time | |
650 | 4 | |a beamforming | |
650 | 4 | |a directional signal extraction | |
650 | 4 | |a microphone array | |
650 | 4 | |a signal separation | |
700 | 1 | |a Patel, Kashyap |e verfasserin |4 aut | |
700 | 1 | |a Panahi, Issa |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t IEEE access : practical innovations, open solutions |d 2013 |g 11(2023) vom: 11., Seite 4350-4358 |w (DE-627)NLM243194919 |x 2169-3536 |7 nnns |
773 | 1 | 8 | |g volume:11 |g year:2023 |g day:11 |g pages:4350-4358 |
856 | 4 | 0 | |u http://dx.doi.org/10.1109/access.2023.3235948 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 11 |j 2023 |b 11 |h 4350-4358 |