A vector Taylor series approach for environment-independent speech recognition

Abstract

In this paper we introduce a new analytical approach to environment compensation for speech recognition. Previous attempts at solving analytically the problem of noisy speech recognition have either used an overly-simplified mathematical description of the effects of noise on the statistics of speech or they have relied on the availability of large environment-specific adaptation sets. Some of the previous methods required the use of adaptation data that consists of simultaneouslyrecorded or "stereo" recordings of clean and degraded speech.In this work we introduce the use of a Vector Taylor series (VTS) expansion to characterize efficiently and accurately the effects on speech statistics of unknown additive noise and unknown linear filtering in a transmission channel. The VTS approach is computationally efficient. It can be applied either to the incoming speech feature vectors, or to the statistics representing these vectors. In the first case the speech is compensated and then recognized; in the second case HMM statistics are modified using the VTS formulation. Both approaches use only the actual speech segment being recognized to compute the parameters required for environmental compensation.We evaluate the performance of two implementations of VTS algorithms using the CMU SPHINX-II system on the 100-word alphanumeric CENSUS database and on the 1993 5000-word ARPA Wall Street Journal database. Artificial white Gaussian noise is added to both databases. The VTS approaches provide significant improvements in recognition accuracy compared to previous algorithms. INTRODUCTIONAs speech recognition systems become more accurate and more sophisticated, robustness to noise, channel, and other environmental effects becomes increasingly important. In the past few years, researchers at CMU and other sites have developed a series of techniques to address this problem. Many of these environment compensation algorithms take advantage of the availability of "stereo data", i.e. speech databases that are simultaneously recorded in high-quality and degraded environments (e.g. [1][2]). Other algorithms make use of non-simultaneously-recorded adaptation data from the degraded environment (e.g. [5]

Uncertainty decoding on Frequency Filtered parameters for robust ASR

“…The approximation in eq. (13) fulfills this objective and avoids the use of more complex approximations such as, for example, VTS (Vector Taylor Series) (Moreno et al (1996)). …”

Investigation and Development of Methods for Improving Robustness of Automatic Speech Recognition Algorithms in Complex Acoustic Environments

“…The most noticeable techniques among them are SPLICE (stereo-piecewise linear compensation for environment) [14], which uses statistics of joint speech and noisy features distribution to construct piecewise linear transform from noisy to clean speech features, and VTS (Vector Taylor Series) [15] which uses approximate linearization of nonlinear model of speech distortion by noise and channel to construct similar transform.…”

The synergy between bounded-distance HMM and spectral subtraction for robust speech recognition

“…In general, these methods were originally developed for improving the speech quality, but they do not necessarily improve the recognition performance (see Gong (1995)). This second category includes popular methods such as spectral subtraction (Boll (1979)), VTS (Vector Tailor Series) (Moreno et al (1996)) or SPLICE (Deng et al (2000)). …”