2011 · 69 citations · 10 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingHidden Markov ModelsLanguage ModelingLanguage ModelsSpeech RecognitionUnsupervised LearningClusteringGaussian Mixture ModelsHidden Markov Model TrainingPhoneme RecognitionSubword ModelingSubword RepresentationSurprise TermsTraining
Can we automatically discover speaker independent phonemelike subword units with zero resources in a surprise language? There have been a number of recent efforts to automatically discover repeated spoken terms without a recognizer. This paper investigates the feasibility of using these results as constraints for unsupervised acoustic model training. We start with a relatively small set of word types, as well as their locations in the speech. The training process assumes that repetitions of the same (unknown) word share the same (unknown) sequence of subword units. For each word type, we train a whole-word hidden Markov model with Gaussian mixture observation densities and collapse correlated states across the word types using spectral clustering. We find that the resulting state clusters align reasonably well along phonetic lines. In evaluating cross-speaker word similarity, the proposed techniques outperform both raw acoustic features and language-mismatched acoustic models.
10
Towards multi-speaker unsupervised speech pattern discovery
Yaodong Zhang, James Glass · 2010 · 77 citations