Logo des Repositoriums
 
Konferenzbeitrag

Speech recognition as a retrieval problem

Lade...
Vorschaubild

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2013

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik e.V.

Zusammenfassung

Common approaches to automatic speech recognition (ASR) are based on training statistical models for the acoustics of speech. In our work, a retrieval-based ASR system is developed that does not rely on training and thus provides more flexible application. It is based on a set of known reference word utterances for each possibly occurring word in a test string. A test word string is identified by finding the most similar reference for each word by using an approach based on dynamic time warping (DTW). The DTW variant suitable for recognizing strings of connected words is called level-building DTW, proposed by Myers and Rabiner in 1981. It is using a level-bylevel iteration to match each word in the test utterance with the most similar reference. In our work, an ASR system for connected digit recognition based on level-building DTW is developed, evaluated and compared with a state-of-the-art HMM recognizer.

Beschreibung

Rieber, Joscha Simon; Bardeli, Rolf (2013): Speech recognition as a retrieval problem. INFORMATIK 2013 – Informatik angepasst an Mensch, Organisation und Umwelt. Bonn: Gesellschaft für Informatik e.V.. PISSN: 1617-5468. ISBN: 978-3-88579-614-5. pp. 2958-2971. Regular Research Papers. Koblenz. 16.-20. September 2013

Schlagwörter

Zitierform

DOI

Tags