IEEE Transactions on Speech and Audio Processing · 1996 · 10 citations · 9 references
ComputingComputer ScienceComputational AcousticsMachine LearningStatistical LearningDigital Signal ProcessingHidden Markov ModelsPattern RecognitionSpeech RecognitionDiscrete ModelsDiscrete Observation ModelsMaximum Mutual InformationMutual Information EstimationSpeech Pattern RecognitionSpeech Recognition AcousticsVector Quantization
Research on multiple vector quantization (MVQ) has shown the suitability of such a technique for speech recognition. Basically, MVQ proposes the use of one separate VQ codebook for each recognition unit. Thus, a MVQHMM model is composed of a VQ codebook and a discrete HMM model. This technique allows the incorporation in the recognition dynamics of the input sequence information wasted by discrete HMM models in the VQ process. The use of distinct codebooks also allows one to train them in a discriminative manner. We propose a new VQ codebook design method for MVQ-based systems, obtained from a modified maximum mutual information estimation. This method provides meaningful error reductions and is performed independently from the estimation of the discrete HMM part of the MVQ model. The results show that the proposed discriminative design turns the MVQHMM technique into a powerful acoustic modeling tool in comparison with other classical methods such as discrete or semicontinuous HMMs.
9
Teuvo Kohonen · Proceedings of the IEEE · 1990 · 8.2K citations
Pattern Classification and Scene Analysis
Michael Thompson, Richard O. Duda, Peter E. Hart · Leonardo · 1974 · 4.5K citations