A new verification-based fast-match for large vocabulary continuous speech recognition

Acoustic fast-match is a popular way to accelerate the search in large-vocabulary continuous-speech recognition, where an efficient method is used to identify poorly scoring phonemes and discard them from detailed evaluation. In this paper we view acoustic fast-match as a verification problem, and hence develop an efficient likelihood ratio test, similar to other verification scenarios, to perform the fast match. Various aspects of the test like the design of alternate hypothesis models and the setting of phoneme look-ahead durations and decision thresholds are studied, resulting in an efficient implementation. The proposed fast-match is tested in a large vocabulary speech recognition task and it is demonstrated that depending on the decision threshold, it leads to 20-30% improvement in speed without any loss in recognition accuracy. In addition, it significantly outperforms a similar test based on using likelihoods only, which fails, in our setting, to bring any improvement in speed-accuracy trade-off. In a larger set of experiments with varying acoustic and task conditions, similar improvements are observed for the fast-match with the same model and setting. This indicates the robustness of the proposed technique. The gains due to the proposed method are obtained within a highly efficient 2-pass search strategy and similar or even higher gains are expected in other alternative search architectures.

I. Introduction

The last decade has witnessed increased interest in the verification problem among the speech research community. The term verification encompasses a wide range of technologies that have important practical applications. Simply stated, verification reduces to the acceptance or rejection of a certain claim. For example, speaker verification (SV) [1] deals with accepting or rejecting a speaker's identity using voice, verbal information verification (VIV) [2] relates to the approval or denial of user's speech password, and utterance verification (UV) [3] focuses on assessing, again for acceptance or rejection, the output of speech recognition systems. This interest has led to the development of new techniques that improved the performance of verification-based systems.