Speaker-Independent Phone Recognition Using BREF

Speaker-Independent Phone Recognition Using BREF Jean-Luc Gauvain and Lori F. Lamel LIMSI-CNRS, BP 133 91403 Orsay cedex, FRANCE ABSTRACT A series of experiments on speaker-independent phone recogni- tion of continuous speech have been carried out using the recently recorded BREF corpus. These experiments are the first to use this large corpus, and are meant to provide a baseline performance eval- uation for vocabulary-independent phone recognition of French. The HMM-based recognizer was trained with hand-verified data from 43 speakers. Using 35 context-independent phone models, a baseline phone accuracy of 60% (no phone grammar) was ob- tained on an independent test set of 7635 phone segments from 19 new speakers. Including phone bigram probabilities as phonotactic constraints resulted in a performance of 63.5%. A phone accuracy of 68.6% was obtained with 428 context dependent models and the bigram phone language model. Vocabulary-independent word recognition results with no grammar are also reported for the same test data. INTRODUCTION This paper reports on a series of experiments for speaker- independent, continuous speech phone recognition of French, using the recently recorded BREF corpus[4, 6]. BREF was designed to provide speech data for the development of dictation machines, the evaluation of continuous speech recognition systems (both speaker-dependent and speaker- independent), and to provide a large corpus of continuous speech to study phonological variations. These experiments are the first to use this corpus, and are meant to provide a baseline performance evaluation for vocabulary-independent (VI) phone recognition, as well as the development of a pro- cedure for automatic segmentation and labeling of the corpus. First a brief description of BREF is given, along with the procedure for semi-automatic (verified) labeling and auto- matic segmentation of the speech data. The ability to accu- rately predict the phone labels from the text is assessed, as is the accuracy of the automatic segmentation. Next the phone recognition experiments performed using speech data from 62 speakers (43 for training, 19 for test) are described. A hid- den Markov model (HMM) based recognizer has beeen eval- uated with context-independent (CI) and context-dependent (CD) model sets, both with and without a duration model. Results are also given with and without the use of 1-gram and 2-gram statistics to provide phonotactic constraints. Pre- liminary VI word recognition results are presented with no grammar. The final section provides a discussion and sum- mary, and a comparison of these results to the performance of other phone recognizers. THE BREF CORPUS BREF is a large read-speech corpus, containing over 100 hours of speech material, from 120 speakers. The text ma- terials were selected verbatim from the French newspaper Le Monde, so as to provide a large vocabulary (over 20,000 words) and a wide range of phonetic environments[4]. Con- taining 11 i5 distinct diphones and over 17,500 triphones, BREF can be used to train VI phonetic models. Hon and Lee[5] concluded that for VI recognition, the coverage of triphones is crucial. Separate text materials, with similar dis- tributionalproperties were selected for training, development test, and evaluation purposes. The …

Content truncated to 500 words