This paper describes our participation in the TREC-9 Spoken Document Retrieval (SDR) track. The THISL SDR system consists of a realtime version of a hybrid connectionist/HMM large vocabulary speech recognition system and a probabilistic text retrieval system. This paper describes the configuration of the speech recognition and text retrieval systems, including segmentation and query expansion. We report our results for development tests using the TREC-8 queries, and for the TREC-9 evaluation. 1.

Our principle ohjcctive was to reduce tile error rate of speech recognition systems used by professional translators. Our work concentrated oil Spanish4o-English translation.

A common problem with current automatic speech recognition (ASR) systems is that the performance degrades when it is presented with speech from a different acoustic environment than the one used during training. An important cause is that the feature distribution to which the ASR system is trained no longer matches that of a new environment. Reverberant environments can be especially harmful. In this work, we test a multi-stream system in which the constituent streams are each trained in separate acoustic environments. When training the acoustic modeling stages of the streams separately with clean data and heavily reverberated data, we find that that the combined system can improve the ASR performance with unseen reverberated test data.

Frame accuracy is a common and natural summary statistic to use in neural-network-based ASR. It is often used as an indication of the performance of the neural network probability estimator and in the stopping criterion during its training. Though considered an important factor for word recognition, the frame accuracy presents an incomplete and sometimes deficient indicator of performance for the overall task of word recognition, as with many such summary statistics. Many in the ASR community have seen instances where an improvement in the acoustic posterior probability estimation yielded a disappointing effect on word recognition. We conducted experiments in an effort to illustrate some of the variability in word-recognition performance associated with frame accuracy. Our experiments attempt to shed light on some of the factors that might give rise to instances where frame accuracy and word error correlate. Some of the results are confirmation of intuitive or commonly known trends.

Our principle objective was to reduce the error rate of speech recognition systems used by professional translators. Our work concentrated on Spanish-to-English translation. In a baseline study we estimated the error rate of an off-the-shelf recognizer to be 9.98%. In this paper we describe two independent methods of improving speech recognizers: a machine translation (MT) method and a topic-based one. An evaluation of the MT method suggests that the vocabulary used for recognition cannot be completely restricted to the set of translations produced by the MT system and a more sophisticated constraint system must be used. An evaluation of the topic-based method showed significant error rate reduction, to 5.07%. Introduction Our goal is to improve the throughput of professional translators by using speech recognition. The problem with using current offthe -shelf speech recognition systems is that these systems have high error rates for similar tasks. If the task is sim...