Szczegóły publikacji
Opis bibliograficzny
On the extraction of early reflection signals for automatic speech recognition / Konrad KOWALCZYK, Stanisław KACPRZAK, Mariusz ZIÓŁKO // W: 2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP) : August 4–6, 2017, Singapore / IEEE. — Piscataway, NJ : IEEE, cop. 2017. — ISBN: 978-1-5386-0968-2; e-ISBN: 978-1-5386-0969-9. — S. 351–355. — Bibliogr. s. 355, Abstr. — Publikacja dostępna online od: 2017-12-01
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
ID BaDAP | 111583 |
---|---|
Data dodania do BaDAP | 2018-02-05 |
Tekst źródłowy | URL |
DOI | 10.1109/SIPROCESS.2017.8124563 |
Rok publikacji | 2017 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
Konferencja | 2017 IEEE 2nd International Conference on Signal and Image Processing |
Abstract
Room reverberation caused by multipath sound wave propagation in acoustic enclosures constitutes an unwanted distortion for automatic speech recognition systems. Multichannel speech enhancement methods often aim to enhance the signal impinging at the microphone array from the source direction while reducing late reverberation. In this paper, we investigate the applicability of spatial filters which constructively combine the direct-path signal with distinct early room reflection signals to increase the direct-to-reverberation ratio and to reduce the word error rate (WER) of automatic speech recognition systems. We present suitable filters and compare them with existing approaches. Results for the simulated acoustic environments indicate that an improvement in WER can indeed be achieved by the spatial filters which account for strong early reflections.