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
TL;DR: In this article, the authors discuss some research directions for ASR that may not always yield an immediate and guaranteed decrease in error rate but which hold some promise for ultimately improving performance in the end applications, including discrimination between rival utterance models, the role of prior information in speech recognition, merging the language and acoustic models, feature extraction and temporal information, and decoding procedures reflecting human perceptual properties.
182 citations
30 Mar 2009
TL;DR: In this article, a synchronous context free grammars (SCFGs) are used for statistical machine translation. And the toolkit achieves state-of-the-art performance on the WMT09 French-English translation task.
Abstract: We describe Joshua, an open source toolkit for statistical machine translation. Joshua implements all of the algorithms required for synchronous context free grammars (SCFGs): chart-parsing, n-gram language model integration, beam-and cube-pruning, and k-best extraction. The toolkit also implements suffix-array grammar extraction and minimum error rate training. It uses parallel and distributed computing techniques for scalability. We demonstrate that the toolkit achieves state of the art translation performance on the WMT09 French-English translation task.
182 citations
05 Jun 2000
TL;DR: The paper investigates the estimation of word posterior probabilities based on word lattices and presents applications of these posteriors in a large vocabulary speech recognition system and a novel approach to integrating these word posterior probability distributions into a conventional Viterbi decoder is presented.
Abstract: The paper investigates the estimation of word posterior probabilities based on word lattices and presents applications of these posteriors in a large vocabulary speech recognition system. A novel approach to integrating these word posterior probability distributions into a conventional Viterbi decoder is presented. The problem of the robust estimation of confidence scores from word posteriors is examined and a method based on decision trees is suggested. The effectiveness of these techniques is demonstrated on the broadcast news and the conversational telephone speech corpora where improvements both in terms of word error rate and normalised cross entropy were achieved compared to the baseline HTK evaluation systems.
182 citations
TL;DR: The experimental results show that the weighted cepstral distance measure works substantially better than both the Euclidean cepStral distance and the log likelihood ratio distance measures across two different databases.
Abstract: A weighted cepstral distance measure is proposed and is tested in a speaker-independent isolated word recognition system using standard DTW (dynamic time warping) techniques. The measure is a statistically weighted distance measure with weights equal to the inverse variance of the cepstral coefficients. The experimental results show that the weighted cepstral distance measure works substantially better than both the Euclidean cepstral distance and the log likelihood ratio distance measures across two different databases. The recognition error rate obtained using the weighted cepstral distance measure was about 1 percent for digit recognition. This result was less than one-fourth of that obtained using the simple Euclidean cepstral distance measure and about one-third of the results using the log likelihood ratio distance measure. The most significant performance characteristic of the weighted cepstral distance was that it tended to equalize the performance of the recognizer across different talkers.
181 citations
TL;DR: In this article, the authors proposed the use of temporal convolution, in the form of time-delay neural network (TDNN) layers, along with unidirectional LSTM layers to limit the latency to 200 ms.
Abstract: Bidirectional long short-term memory (BLSTM) acoustic models provide a significant word error rate reduction compared to their unidirectional counterpart, as they model both the past and future temporal contexts. However, it is nontrivial to deploy bidirectional acoustic models for online speech recognition due to an increase in latency. In this letter, we propose the use of temporal convolution, in the form of time-delay neural network (TDNN) layers, along with unidirectional LSTM layers to limit the latency to 200 ms. This architecture has been shown to outperform the state-of-the-art low frame rate (LFR) BLSTM models. We further improve these LFR BLSTM acoustic models by operating them at higher frame rates at lower layers and show that the proposed model performs similar to these mixed frame rate BLSTMs. We present results on the Switchboard 300 h LVCSR task and the AMI LVCSR task, in the three microphone conditions.
181 citations