Phonetic Classification on Wide-Band and Telephone Quality Speech

PHONETIC CLASSIFICATION ON WIDE-BAND AND TELEPHONE QUALITY SPEECH Benjamin Chigier Speech Technology Group Artificial Intelligence Laboratory NYNEX Science and Technology White Plains, NY, 10604, U.S.A. 1. ABSTRACT Benchmarking the performance for telephone-network-based speech recognition systems is hampered by two factors: lack of standardized databases for telephone network speech, and insuffi- cient understanding of the impact of the telephone network on rec- ognition systems. The N-TIMIT database was used in the experiments described in this paper in order to "calibrate" the effect of the telephone network on phonetic classification algo- fithrns. Phonetic classification algorithms have been developed for wide-band and telephone quality speech, and were tested on sub- sets of the TIMIT and N-TIMIT databases. The classifier described in this paper provides accuracy of 75% on wide-band TIM1T data and 66.5% on telephone quality N-TIMIT data. Over- all the telephone network seems to increase the error rate by a fac- tor of 1.3. 2. INTRODUCTION Researchers typically make use of standardized databases in order to benchmark the performance of speech recogni- tion/understanding systems between and within laborato- ries. Comparisons between laboratories are important in order to benchmark the progress of the field in general. Comparisons within a laboratory are important to bench- mark progress as a function of the research-and-develop- ment cycle. Benchmarking phonetic classification algorithms for telephone-network-based speech recogni- tion/understanding systems poses two problems. First, there is no commonly-accepted standard database for evaluating phonetic classification for telephone quality speech. As a result, few if any inter-laboratory comparisons have been made. Second, the telephone network presents speech rec- ognition/understanding systems with a band-limited, noisy, and in some cases distorted speech signal. While we would like to benchmark the performance of recognition systems intended for network speech against that of systems intended for wide-band speech, we do not have adequate quantification of the impact of the telephone network's sig- nal degradation on the performance of phonetic classifica- tion algorithms. Therefore, we do not know whether the performance of a telephone-speech classification algorithm is limited by characteristics of the algorithm(s) or by char- actedstics of the test utterances themselves. Both problems noted above could be addressed given a standardized database in which the speech data is presented in two forms: speech with wide-band characteristics and the same speech data with telephone network characteris- tics. As reported in Jankowski et al. [1], the N-TIMIT data- base was created for this purpose. The N-TIMIT database is identical to TIMIT [2] except that the former has been transmitted over the telephone network. Figure 1 shows a sample spectrogram of a TIMIT and N-TIMIT utterance. The N-TIMIT versions were recorded over many different transmission paths in order to get a representative sample of the range of telephone network conditions. This data presents a platform to "calibrate" the impact of the tele- phone network on the performance of phonetic classifica- tion algorithms. The telephone network affects the speech signal it carries in many ways. Chigier and Spitz[3] discussed the possible effects of source characteristics (how the speech is …

Content truncated to 500 words