Adaptation to New Microphones Using Tied-Mixture Normalization

ADAPTATION TO NEW MICROPHONES USING TIED-MIXTURE NORMALIZATION Anastasios Anastasakost, Francis Kubala, John Makhoul, Richard Schwartz ABSTRACT BBN Systems and Technologies Cambridge MA 02138 tNortheastem University Boston MA 02115 In this paper, we present several approaches designed to increase the robustness of BYBLOS, the BBN continuous speech recogni- tion system. We address the problem of increased degradation in • performance when there is mismatch in the characteristics of the training and the test microphones. We introduce a new supervised adaptafi.~n algor/thm that computes a transformation from the train- hag microphone codebook to that of a new microphone, given some information about the new microphone. Results are reported for the development and evaluation test sets of the 1993 ARPA CSR Spoke 6 WSJ task, which consist of speech recorded with two al- • temate microphones, a stand-mount and a telephone microphone. The proposed algorithm improves the performance of the system • • when tested with the stand-mount microphone by reducing the dif- ference ha error rate between the high quality training microphone and the alternate stand-mount microphone recordings by a factor of 2. Several results are presented for the telephone speech leading • to important conclusions: a) the performance on telephone speech is dramaticaUy improved by simply retraining the system on the high-quality training data after they have been bandlimited in the telephone bandwith; and b) additional training data recorded with the high quality microphone give luther substantial improvement ha performance. 1. INTRODUCTION Interactive speech recognition systems are usually trained on substantial amounts of speech data collected with a high quality close-talking microphone. During recognition, these systems require the same type of microphone to be used in order to achieve their standard accuracy. This is a highly re- stdcting condition for practical applications of speech recog- nition systems. One can imagine a situation, where it would be desirable to use a different microphone for recognition than the one with which the training speech was collected. For example, some users may not want to wear a head- molmted microphone. Others may not want to pay for a high quality microphone. Additionally, many applications involve recognition of speech over telephone lines and tele- phone sets with high variability in quality and characteristics. However, we know that even highly accurate speech recog- nition systems perform very poorly when they are tested with microphones with different characteristics than the ones that they were trained on [1]. There is a wide range of approaches in order to compensate for this degradation in performance including: Retrain the HMMs with data collected with the new microphone encountered during the recognition stage, a rather expensive approach for real applications, or by training on a large number of microphones in the hope that the system will obtain the necessary robustness. Use robust signal processing algorithms. Develop a feature transformation that maps the alternate microphone data to training microphone data. Use statistical methods in order to adapt the parameters of the acoustic models. In previous work we had discussed the use of …

Content truncated to 500 words