Combining acoustic and articulatory feature information for robust speech recognition

Kirchhoff K, Fink GA, Sagerer G (2002)
Speech Communication 37(3-4): 303-319.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Autor/in
; ;
Abstract / Bemerkung
The idea of using articulatory representations for automatic speech recognition (ASR) continues to attract much attention in the speech community. Representations which are grouped under the label "articulatory" include articulatory parameters derived by means of acoustic-articulatory transformations (inverse filtering), direct physical measurements or classification scores for pseudo-articulatory features. In this study, we revisit the use of features belonging to the third category. In particular, we concentrate on the potential benefits of pseudo-articulatory features in adverse acoustic environments and on their combination with standard acoustic features. Systems based on articulatory features only and combined acoustic-articulatory systems are tested on two different recognition tasks: telephone-speech continuous numbers recognition and conversational speech recognition. We show that articulatory feature (AF) systems are capable of achieving a superior performance at high noise levels and that the combination of acoustic and AFs consistently leads to a significant reduction of word error rate across all acoustic conditions. (C) 2002 Elsevier Science B.V. All rights reserved.
Stichworte
neural networks; speech recognition; articulatory representations; classifier combination
Erscheinungsjahr
2002
Zeitschriftentitel
Speech Communication
Band
37
Ausgabe
3-4
Seite(n)
303-319
ISSN
0167-6393
Page URI
https://pub.uni-bielefeld.de/record/1614268

Zitieren

Kirchhoff K, Fink GA, Sagerer G. Combining acoustic and articulatory feature information for robust speech recognition. Speech Communication. 2002;37(3-4):303-319.
Kirchhoff, K., Fink, G. A., & Sagerer, G. (2002). Combining acoustic and articulatory feature information for robust speech recognition. Speech Communication, 37(3-4), 303-319. doi:10.1016/S0167-6393(01)00020-6
Kirchhoff, K., Fink, G. A., and Sagerer, G. (2002). Combining acoustic and articulatory feature information for robust speech recognition. Speech Communication 37, 303-319.
Kirchhoff, K., Fink, G.A., & Sagerer, G., 2002. Combining acoustic and articulatory feature information for robust speech recognition. Speech Communication, 37(3-4), p 303-319.
K. Kirchhoff, G.A. Fink, and G. Sagerer, “Combining acoustic and articulatory feature information for robust speech recognition”, Speech Communication, vol. 37, 2002, pp. 303-319.
Kirchhoff, K., Fink, G.A., Sagerer, G.: Combining acoustic and articulatory feature information for robust speech recognition. Speech Communication. 37, 303-319 (2002).
Kirchhoff, Katrin, Fink, Gernot A., and Sagerer, Gerhard. “Combining acoustic and articulatory feature information for robust speech recognition”. Speech Communication 37.3-4 (2002): 303-319.