Frequency-dependent speaker detection using a microphone array
- In this paper we propose a method to determine the active speaker for each time-frequency point in the noisy signals of a microphone array. This detection is based on a statistical model where the speech signals as well as noise signals are assumed to be multivariate Gaussian random variables in the Fourier domain. Based on this model we derive a maximum-likelihood detector for the active speaker. The decision is based on the a posteriori signal to noise ratio (SNR) of a speaker dependent max-SNR beamformer.
| Author: | Jürgen FreudenbergerORCiDGND, Simon GrimmGND |
|---|---|
| URL: | http://pub.dega-akustik.de/DAGA_2016/data/index.html |
| ISBN: | 978-3-939296-10-2 |
| Parent Title (English): | Fortschritte der Akustik : DAGA 2016, Aachen : 14.-17. März 2016 : 42. Jahrestagung für Akustik, Tagungsband |
| Publisher: | Dt. Gesellschaft für Akustik e.V. |
| Place of publication: | Berlin |
| Document Type: | Conference Proceeding |
| Language: | English |
| Year of Publication: | 2016 |
| Release Date: | 2018/11/23 |
| Tag: | Sprachakustik |
| First Page: | 940 |
| Last Page: | 943 |
| Open Access?: | Ja |
| Relevance: | Keine peer reviewed Publikation (Wissenschaftlicher Artikel und Aufsatz, Proceeding, Artikel in Tagungsband) |
