New Results with the Lincoln Tied-Mixture HMM CSR System

The following describes recent work on the Lincoln CSR system. Some new variations in semiphone modeling have been tested. A very simple improved duration model has reduced the error rate by about 10~ in both triphone and semiphone systems. A new training strategy has been tested which, by itself, did not provide useful improvements but suggests that improvements can be obtained by a related rapid adaptation technique. Finally, the recognizer has been modified to use bigram back-off language models. The system was then transferred from the RM task to the ATIS CSR task and a limited number of development tests performed. Evaluation test results are presented for both the RM and ATIS CSR tasks. I N T R O D U C T I O N The following experiments are all carried out in the context of the Lincoln tied-mixture (TM) hidden Markov model (HMM) continuous speech recognition (CSR) system. This system uses two observation streams (TM-2) for speaker-dependent (SD) recognition: mel-cepstra and time differential mel-cepstra. For speaker-independent (SI) recognition, a second differential mel-cepstral observation stream is added (TM-3). The system uses Gaussian tied mixture [1, 2] observation pdfs and treats each observation stream as if it is statistically independent of all others. Triphone models [14], including cross-word triphone models [10, 7, 16], are used to model phonetic coarticulation. These models are smoothed with reduced context phone models [14]. Each phone model is a three state "linear" (no skip transitions) HMM. The phone models are trained by the forward-backward algorithm using an unsupervised monophone (context independent phone) bootstrapping procedure. The recognizer extrapolates (estimates) untrained phone models and recognizes using a Viterbi beam search. The initial implementation uses finite-state grammars, contains an adaptive background model, and allows optional inter-word silences. All RM1 development tests use the designated SD development test set (100 sentences x 12 speak1This work was sponsored by the Defense Advanced Research Projects Agency. ers) and all RM2 tests use the designated development test set (120 sentences x 4 speakers).