Field Test Evaluations and Optimization of Speaker Independent Speech Recognition for Telephone Applications

FIELD TEST EVALUATIONS and OPTIMIZATION of SPEAKER INDEPENDENT SPEECH RECOGNITION for TELEPHONE APPLICATIONS Christian GA GNOULET and Christel SORIN CNET D6pt RCP 22301 LANNION-France ABSTRACT This paper presents, in a first part, the detailed results of several field evaluations of the CNET speaker independent speech recognition system in a context of 2 voice-activatedservers accessible by the general French public over the telephone. The analysis of roughly ll 000 user's tokens indicates that the rejection of incorrect input is a major problem and that the gap between the recognition rates observed in real use conditions and in the most "realistic" laboratory tests remains very large. The second part of the paper describes the current improvements of the system : better rejection procedures, enhancement of the recognition performances resulting from both the introduction of field data in the training data and the increase of the number of parameters, automatic adjustments of the HMM topology allowing to either reduce overall model complexity or improve recognition performance. Tested on long distance telep.hone databases (450 to 750 speakers), the current version of the CNET recognition system yields a laboratory error rate of 0.7 % on the 10 French digits and of 0.95 % on a 36 word vocabulary. INTRODUCTION At CNET, the speech recognition studies are specifically oriented toward the development of telecommunications applications. This implies the development of robust, speaker independent speech recognition systems but also the design and the evaluation of complete spoken dialogue systems, for which human factor studies are essential. SYSTEM OVERVIEW and FIELD TEST EVALUATIONS System overview The connected speech recognition algorithm developed at CNET in 1986 [1] uses the HMM approach and has been implemented on several devices (RDP 20 and RDP 50 boards) [2]. In the implemented version of the algorithm, 6 Mel cepstral coefficients, the energy and its derivative are computed every 16 ms to obtain the input vectors. The observation probabilities are represented by gaussian functions with diagonal covariance matrices and are tied to the transitions of the Markov chains. Various kinds of modellinlg can be implemented : either word units or sub- word units such as phonemes, diphones or allophones. For each application, the network is fully compiled and includes imtial and final silence models for each word. This system has been tested on several databases of isolated and connected words recorded over the telephone network with willing subjects (mainly long distance lines, speakers representing different regional accents) : DIGITS-1 (455 speakers, 10 French digits), NUMBERS (730 speakers, 00...99 in French), TREGOR (513 speakers, 36 French words). For each database, one half of the data was used for training, the other half for testing. Using word models, the obtained word error rates (for the first version of the system) were 2.1% for DIGITS-l, 2.7 % for TREGOR and 9.6 % for NUMBERS. Field test evaluations Experimental server" MAIRIE-VOX In 1988, an experimental, one-port voice interactive system, MAIRIEVOX [3], was built on a PC computer using the RDP 50 board (word models, 13 states/word, 3 ~gaussian …

Content truncated to 500 words