1998 · 220 citations · 10 references
ComputingComputer ScienceStatistical ModelingStochastic ModelingStochastic ProcessesBayesian InferenceBayesian LearningBayesian Model BuildingBayesian StatisticsSpeech RecognitionStochastic Systems ModelingAutomatic RecognitionBayesian Dynamic ModelsBayesian NetworksComputational EfficiencyConditional IndependenceConditional Independence AssumptionSpeech Pattern RecognitionStochastic State-space Models
Dynamic Bayesian networks (DBNs) are a useful tool for representing complex stochastic processes. Recent developments in inference and learning in DBNs allow their use in real-world applications. In this paper, we apply DBNs to the problem of speech recognition. The factored state representation enabled by DBNs allows us to explicitly represent long-term articulatory and acoustic context in addition to the phonetic-state information maintained by hidden Markov models (HMMs). Furthermore, it enables us to model the short-term correlations among multiple observation streams within single time-frames. Given a DBN structure capable of representing these long- and short-term correlations, we applied the EM algorithm to learn models with up to 500,000 parameters. The use of structured DBN models decreased the error rate by 12 to 29% on a large-vocabulary isolated-word recognition task, compared to a discrete HMM; it also improved significantly on other published results for the same task. Th...
10
Factorial Hidden Markov Models
Zoubin Ghahramani, Michael I. Jordan · Machine Learning · 1997 · 1.2K citations · Full text
A model for reasoning about persistence and causation
Thomas Dean, Keiji Kanazawa · Computational Intelligence · 1989 · 999 citations