2007 · 186 citations · 13 references
ComputingLinguisticsComputational LinguisticsNatural Language ProcessingPhoneticsLanguage ModelingLanguage ModelsMachine TranslationSequence AlignmentSpeech RecognitionSpeech SynthesisDouble LettersHidden Semi-markov ModelsWord Alignment
Letter-to-phoneme conversion generally requires aligned training data of letters and phonemes. Typically, the alignments are limited to one-to-one alignments. We present a novel technique of training with many-to-many alignments. A letter chunking bigram prediction manages double letters and double phonemes automatically as opposed to preprocessing with fixed lists. We also apply an HMM method in conjunction with a local classification model to predict a global phoneme sequence given a word. The many-to-many alignments result in significant improvements over the traditional one-to-one approach. Our system achieves state-of-the-art performance on several languages and data sets. 1
13
Instance-Based Learning Algorithms
David W. Aha, Dennis Kibler, Marc K. Albert · Machine Learning · 1991 · 4.1K citations · Full text
Discriminative training methods for hidden Markov models
Michael Collins · 2002 · 1.9K citations · Full text
Parallel Networks that Learn to Pronounce English Text
Terrence J. Sejnowski · 1987 · 1.6K citations