Distant speech recognition in reverberant noisy conditions employing a microphone array

Juan Andrés Morales Cordovilla, Martin Hagmüller, Hannes Pessentheiner, Gernot Kubin

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

Abstract

This paper addresses the problem of distant speech recognition in reverberant noisy conditions employing a microphone array. We present a prototype system that can segment the utterances in real-time and generate robust ASR results off-line. The segmentation is carried out by a voice activity detector based on deep belief networks, the speaker localization by a position-pitch plane, and the enhancement by a novel combination of convex optimized beamforming and vector Taylor series compensation. All of the components are compared with other similar ones and justified in terms of word accuracy on a proposed database which simulates distant speech recognition in a home environment
Originalspracheenglisch
Titel22nd European Signal Processing Conference
Seiten2380-2384
ISBN (elektronisch)9780992862619
PublikationsstatusVeröffentlicht - 2014
Veranstaltung22nd European Signal Processing Conference: EUSIPCO 2014 - Lisbon, Portugal
Dauer: 1 Sept. 20145 Sept. 2014

Konferenz

Konferenz22nd European Signal Processing Conference
KurztitelEUSIPCO
Land/GebietPortugal
OrtLisbon
Zeitraum1/09/145/09/14

Fields of Expertise

  • Information, Communication & Computing

Treatment code (Nähere Zuordnung)

  • Basic - Fundamental (Grundlagenforschung)
  • Application

Fingerprint

Untersuchen Sie die Forschungsthemen von „Distant speech recognition in reverberant noisy conditions employing a microphone array“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren