Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Near-field source extraction using speech presence probabilities for ad hoc microphone arrays

: Taseska, Maja; Markovich-Golan, Shmulik; Gannot, Sharon; Habets, Emanuël A.P.


Institute of Electrical and Electronics Engineers -IEEE-:
14th International Workshop on Acoustic Signal Enhancement, IWAENC 2014 : Juan-les-Pins, 8-11 September 2014
Piscataway, NJ: IEEE, 2014
ISBN: 978-1-4799-6808-4
International Workshop on Acoustic Signal Enhancement (IWAENC) <14, 2014, Juan-les-Pins>
Fraunhofer IIS ()

Ad hoc wireless acoustic sensor networks (WASNs) hold great potential for improved performance in speech processing applications, thanks to better coverage and higher diversity of the received signals. We consider a multiple speaker scenario where each of the WASN nodes, an autonomous system comprising of sensing, processing and communicating capabilities, is positioned in the near-field of one of the speakers. Each node aims at extracting its nearest speaker while suppressing other speakers and noise. The ad hoc network is characterized by an arbitrary number of speakers/nodes with uncontrolled microphone constellation. In this paper we propose a distributed algorithm which shares information between nodes. The algorithm requires each node to transmit a single audio channel in addition to a soft time-frequency (TF) activity mask for its nearest speaker. The TF activity masks are computed as a combination of estimates of a model-based speech presence probability (SPP), direct to reverberant ratio (DRR) and direction of arrival (DOA) per TF bin. The proposed algorithm, although sub-optimal compared to the centralized solution, is superior to the single-node solution.