First International Conference on Spoken Language Processing (ICSLP 90)

Kobe, Japan
November 18-22, 1990

Acoustical Pre-Processing for Robust Spoken Language Systems

Alejandro Acero, Richard M. Stern

Department of Electrical and Computer Engineering, and School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA

In this paper we discuss several issues that concern the development of spoken language systems that are robust to changes in the acoustical environment. We describe the benefit of joint compensation for differences in noise level and spectral tilt between close-talking and desk-top microphones, as opposed to independent compensation. For Sphinx, the CMU continuous-speech speaker-independent recognition system, cepstral processing offers the advantages of easier integration, greater computationally efficiency and greater accuracy compared to processing in the spectral domain. We also present algorithms that adapt to new environments by estimating noise level and spectral tilt directly from the input speech, without the need for environment-specific training data.

Full Paper

Bibliographic reference.  Acero, Alejandro / Stern, Richard M. (1990): "Acoustical pre-processing for robust spoken language systems", In ICSLP-1990, 1121-1124.