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.

High Threshold Error Correction for the Surface Code

Abstract: An algorithm is presented for error correction in the surface code quantum memory. This is shown to correct depolarizing noise up to a threshold error rate of 18.5%, exceeding previous results and coming close to the upper bound of 18.9%. The time complexity of the algorithm is found to be polynomial with error suppression, allowing efficient error correction for codes of realistic sizes.

A novel feature transformation for vocal tract length normalization in automatic speech recognition

Abstract: This paper proposes a method to transform acoustic models that have been trained with a certain group of speakers for use on different speech in hidden Markov model based (HMM-based) automatic speech recognition. Features are transformed on the basis of assumptions regarding the difference in vocal tract length between the groups of speakers. First, the vocal tract length (VTL) of these groups has been estimated based on the average third formant F/sub 3/. Second, the linear acoustic theory of speech production has been applied to warp the spectral characteristics of the existing models so as to match the incoming speech. The mapping is composed of subsequent nonlinear submappings. By locally linearizing it and comparing results in the output, a linear approximation for the exact mapping was obtained which is accurate as long as the warping is reasonably small. The feature vector, which is computed from a speech frame, consists of the mel scale cepstral coefficients (MFCC) along with delta and delta/sup 2/-cepstra as well as delta and delta/sup 2/ energy. The method has been tested for TI digits data base, containing adult and children speech, consisting of isolated digits and digit strings of different length. The word error rate when trained on adults and tested on children with transformed adult models is decreased by more than a factor of two compared to the nontransformed case.

On a model-robust training method for speech recognition

Abstract: Training methods for designing better decoders are compared. The training problem is considered as a statistical parameter estimation problem. In particular, the conditional maximum likelihood estimate (CMLE), which estimates the parameter values that maximize the conditional probability of words given acoustics during training, is compared to the maximum-likelihood estimate, which is obtained by maximizing the joint probability of the words and acoustics. For minimizing the decoding error rate of the (optimal) maximum a posteriori probability (MAP) decoder, it is shown that the CMLE (or maximum mutual information estimate, MMIE) may be preferable when the model is incorrect. In this sense, the CMLE/MMIE appears more robust than the MLE. >

Minimizing word error rate in textual summaries of spoken language

Abstract: Automatic generation of text summaries for spoken language faces the problem of containing incorrect words and passages due to speech recognition errors. This paper describes comparative experiments where passages with higher speech recognizer confidence scores are favored in the ranking process. Results show that a relative word error rate reduction of over 10% can be achieved while at the same time the accuracy of the summary improves markedly.