Topic
Word error rate
About: Word error rate is a research topic. Over the lifetime, 11939 publications have been published within this topic receiving 298031 citations.
Papers published on a yearly basis
Papers
More filters
25 Aug 2013
TL;DR: A new scalable approach to using deep neural network (DNN) derived features in Gaussian mixture density hidden Markov model (GMM-HMM) based acoustic modeling for large vocabulary continuous speech recognition (LVCSR).
Abstract: We present a new scalable approach to using deep neural network (DNN) derived features in Gaussian mixture density hidden Markov model (GMM-HMM) based acoustic modeling for large vocabulary continuous speech recognition (LVCSR). The DNN-based feature extractor is trained from a subset of training data to mitigate the scalability issue of DNN training, while GMM-HMMs are trained by using state-of-the-art scalable training methods and tools to leverage the whole training set. In a benchmark evaluation, we used 309-hour Switchboard-I (SWB) training data to train a DNN first, which achieves a word error rate (WER) of 15.4% on NIST-2000 Hub5 evaluation set by a traditional DNN-HMM based approach. When the same DNN is used as a feature extractor and 2,000-hour “SWB+Fisher” training data is used to train the GMM-HMMs, our DNN-GMM-HMM approach achieves a WER of 13.8%. If per-conversation-side based unsupervised adaptation is performed, a WER of 13.1% can be achieved.
131 citations
TL;DR: The results of the experiments show that there is only a slight difference between the recognition accuracies for statistical features and dynamic features over the long term, and it is more efficient to use statistical features than dynamic features.
Abstract: This paper describes results of speaker recognition experiments using statistical features and dynamic features of speech spectra extracted from fixed Japanese word utterances. The speech wave is transformed into a set of time functions of log area ratios and a fundamental frequency. In the case of statistical features, a mean value and a standard deviation for each time function and a correlation matrix between these functions are calculated in the voiced portion of each word, and after a feature selection procedure, they are compared with reference features. In the case of dynamic features, the time functions are brought into time registration with reference functions. The results of the experiments show that there is only a slight difference between the recognition accuracies for statistical features and dynamic features over the long term. Since the amount of calculation necessary for recognition using statistical features is only about one-tenth of that for recognition using dynamic features, it is more efficient to use statistical features than dynamic features. When training utterances are recorded over ten months for each customer and spectral equalization is applied, 99.5 percent and 96.3 percent verification accuracies can be obtained for input utterances ten months and five years later, respectively, using statistical features extracted from two words. Combination of dynamic features with statistical features can reduce the error rate to half that obtained with either one alone.
131 citations
TL;DR: The proposed algorithm, called structural MAPLR (SMAPLR), has been evaluated on the Spoke3 1993 test set of the WSJ task and it is shown that SMAPLR reduces the risk of overtraining and exploits the adaptation data much more efficiently than MLLR, leading to a significant reduction of the word error rate for any amount of adaptation data.
131 citations
TL;DR: The methodology is illustrated by comparing different pooling algorithms for the detection of individuals recently infected with HIV in North Carolina and Malawi.
Abstract: We derive and compare the operating characteristics of hierarchical and square array-based testing algorithms for case identification in the presence of testing error. The operating characteristics investigated include efficiency (i.e., expected number of tests per specimen) and error rates (i.e., sensitivity, specificity, positive and negative predictive values, per-family error rate, and per-comparison error rate). The methodology is illustrated by comparing different pooling algorithms for the detection of individuals recently infected with HIV in North Carolina and Malawi.
130 citations
Proceedings Article•
30 Jul 2000
TL;DR: A novel approach to word translation probabilities using the EM algorithm is presented, which extends upon target language modeling and constructs a word translation model for 3830 German and 6147 English noun tokens, with very promising results.
Abstract: Selecting the right word translation among several options in the lexicon is a core problem for machine translation. We present a novel approach to this problem that can be trained using only unrelated monolingual corpora and a lexicon. By estimating word translation probabilities using the EM algorithm, we extend upon target language modeling. We construct a word translation model for 3830 German and 6147 English noun tokens, with very promising results.
130 citations