Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings |
| Seiten | 211-215 |
| Seitenumfang | 5 |
| ISBN (elektronisch) | 9789082797060 |
| Publikationsstatus | Veröffentlicht - 2021 |
| Veranstaltung | 29th European Signal Processing Conference, EUSIPCO 2021 - Dublin, Irland Dauer: 23 Aug. 2021 → 27 Aug. 2021 |
Publikationsreihe
| Name | European Signal Processing Conference |
|---|---|
| Band | 2021-August |
| ISSN (Print) | 2219-5491 |
| ISSN (elektronisch) | 2076-1465 |
Abstract
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Signalverarbeitung
- Ingenieurwesen (insg.)
- Elektrotechnik und Elektronik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings. 2021. S. 211-215 (European Signal Processing Conference; Band 2021-August).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Direction of Arrival Estimation of Noisy Speech using Convolutional Recurrent Neural Networks with Higher-Order Ambisonics Signals
AU - Poschadel, Nils
AU - Hupke, Robert
AU - Preihs, Stephan
AU - Peissig, Jürgen
PY - 2021
Y1 - 2021
N2 - Training convolutional recurrent neural networks on first-order Ambisonics signals is a well-known approach when estimating the direction of arrival for speech/sound signals. In this work, we investigate whether increasing the order of Ambisonics up to the fourth order further improves the estimation performance of convolutional recurrent neural networks. While our results on data based on simulated spatial room impulse responses show that the use of higher Ambisonics orders does have the potential to provide better localization results, no further improvement was shown on data based on real spatial room impulse responses from order two onwards. Rather, it seems to be crucial to extract meaningful features from the raw data. First order features derived from the acoustic intensity vector were superior to pure higher-order magnitude and phase features in almost all scenarios.
AB - Training convolutional recurrent neural networks on first-order Ambisonics signals is a well-known approach when estimating the direction of arrival for speech/sound signals. In this work, we investigate whether increasing the order of Ambisonics up to the fourth order further improves the estimation performance of convolutional recurrent neural networks. While our results on data based on simulated spatial room impulse responses show that the use of higher Ambisonics orders does have the potential to provide better localization results, no further improvement was shown on data based on real spatial room impulse responses from order two onwards. Rather, it seems to be crucial to extract meaningful features from the raw data. First order features derived from the acoustic intensity vector were superior to pure higher-order magnitude and phase features in almost all scenarios.
KW - Convolutional recurrent neural network
KW - Direction of arrival estimation
KW - Higher-order ambisonics
KW - Spherical harmonics
UR - http://www.scopus.com/inward/record.url?scp=85123160520&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2102.09853
DO - 10.48550/arXiv.2102.09853
M3 - Conference contribution
SN - 978-1-6654-0900-1
T3 - European Signal Processing Conference
SP - 211
EP - 215
BT - 29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings
T2 - 29th European Signal Processing Conference, EUSIPCO 2021
Y2 - 23 August 2021 through 27 August 2021
ER -