2005 · 61 citations · 9 references
ComputingComputer ScienceAcousticsMachine LearningNatural Language ProcessingDimensionality ReductionPattern RecognitionSpeech RecognitionSpoken CorporaError Rate AnalysisError Rate MetricsHistogram AnalysisLocal Density ApproximationSpeech Recognition AcousticsWord Error Rate
We describe a technique called histogram normalization that aims at normalizing feature space distributions at different stages in the signal analysis front-end, namely the log-compressed filterbank vectors, cepstrum coefficients, and LDA (local density approximation) transformed acoustic vectors. Best results are obtained at the filterbank, and in most cases there is a minor additional gain when normalization is applied sequentially at different stages. We show that histogram normalization performs best if applied both in training and recognition, and that smoothing the target histogram obtained on the training data is also helpful. On the VerbMobil II corpus, a German large-vocabulary conversational speech recognition task, we achieve an overall reduction in word error rate of about 10% relative.
9
Speaker normalization using efficient frequency warping procedures
Li Lee, Richard C. Rose · 2002 · 262 citations
A parametric approach to vocal tract length normalization
Ellen Eide, H. Gish · 2002 · 260 citations
Efficient cepstral normalization for robust speech recognition
Fuhua Liu, Richard M. Stern, Xuedong Huang et al. · 1993 · 137 citations · Full text