A recent trend in automatic speech recognition systems is the use of continuous mixture-density hidden Markov models (HMM's). Despite the good recognition performance that these systems achieve on average in large vocabulary applications, there is a large variability in performance across speakers. Performance degrades dramatically when the user is radically different from the training population. A popular technique that can improve the performance and robustness of a speech recognition system

more »

... is adapting speech models to the speaker, and more generally to the channel and the task. In continuous mixture-density HMM's the number of component densities is typically very large, and it may not be feasible to acquire a sufficient amount of adaptation data for robust maximum-likelihood estimates. To solve this problem, we propose a constrained estimation technique for Gaussian mixture densities. The algorithm is evaluated on the large-vocabulary Wall Street Journal corpus for both native and nonnative speakers of American English. For nonnative speakers, the recognition error rate is approximately halved with only a small amount of adaptation data, and it approaches the speakerindependent accuracy achieved for native speakers. For native speakers, the recognition performance after adaptation improves to the accuracy of speaker-dependent systems that use six times as much training data. 'By degree of genone sharing we refer to the average number of distinct HMM states that share the same genone's Gaussians in their output distributions.