Efficient Cepstral Normalization for Robust Speech Recognition

EFFICIENT CEPSTRAL NORMALIZATION FOR ROBUST SPEECH RECOGNITION Fu-Hua Liu, Richard M. Stern, Xuedong Huang, Alejandro Acero Department of Electrical and Computer Engineering School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 ABSTRACT In this paper we describe and compare the performance of a series of cepstrum-based procedures that enable the CMU SPHINX-II speech recognition system to maintain a high level of recognition accuracy over a wide variety of acoustical environments. We describe the MFCDCN algorithm, an environment-independent extension of the efficient SDCN and FCDCN algorithms devel- oped previously. We compare the performance of these algorithms with the very simple RASTA and cepstral mean normalization procedures, describing the performance of these algorithms in the context of the 1992 DARPA CSR evaluation using secondary microphones, and in the DARPA stress-test evaluation. 1. INTRODUCTION The need for speech recognition systems and spoken lan- guage systems to be robust with respect to their acoustical environment has become more widely appreciated in recent years (e.g. [1]). Results of many studies have demonstrated that even automatic speech recognition systems that are designed to be speaker independent can perform very poorly when they are tested using a different type of micro- phone or acoustical environment from the one with which they were trained (e.g. [2,3]), even in a relatively quiet office environment. Applications such as speech recogni- tion over telephones, in automobiles, on a factory floor, or outdoors demand an even greater degree of environmental robusmess. Many approaches have been considered in the development of robust speech recognition systems including techniques based on autoregressive analysis, the use of special distor- tion measures, the use of auditory models, and the use of microphone arrays, among many other approaches (as reviewed in [1,4]). In this paper we describe and compare the performance of a series of cepstrum-based procedures that enable the CMU SPHINX-II speech recognition system to maintain a high level of recognition accuracy over a wide variety of acousti- cal environments. The most recently-developed algorithm is multiple fixed codeword-dependent cepstral normaliza- tion (MFCDCN). MFCDCN is an extension of a similar algorithm, FCDCN, which provides an additive environ- mental compensation to cepstral vectors, but in an environ- ment-specific fashion [5]. MFCDCN is less computationally complex than the earlier CDCN algorithm, and more accurate than the related SDCN and BSDCN algorithms [6], and it does not require domain-specific paining to new acoustical environments. In this paper we describe the performance of MFCDCN and related algo- rithms, and we compare it to the popular RASTA approach to robustness. 2. EFFICIENT CEPSTRUM-BASED COMPENSATION TECHNIQUES In this section we describe several of the cepstral normal- ization techniques we have developed to compensate simultaneously for additive noise and linear filtering. Most of these algorithms are completely data-driven, as the com- pensation parameters are determined by comparisons between the testing environment and simultaneously- recorded speech samples using the DARPA standard clos- etalking Sennheiser HMD-414 microphone (referred to as the CLSTLK microphone in this paper). The remaining algorithm, codeword-dependent cepstral normalization (CDCN), is model-based, as …

Content truncated to 500 words