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.

Efficient real-time analysis method of error logs for autonomous systems

Abstract: An error logging and analysis system is used to detect a type of error condition, assign a numeric value corresponding to the severity of the error condition, record the time of the error condition, and determine the frequency between subsequent error conditions of the same type. A weighted error rate is generated as a function of the severity of the initial error condition, the frequency of subsequent error conditions, and a percentage of any preceding weighted error rates. These weighted error rates are compared to a predetermined threshold to determine if the error condition is statistically significant.

Deep Lip Reading: a comparison of models and an online application

Abstract: The goal of this paper is to develop state-of-the-art models for lip reading -- visual speech recognition. We develop three architectures and compare their accuracy and training times: (i) a recurrent model using LSTMs; (ii) a fully convolutional model; and (iii) the recently proposed transformer model. The recurrent and fully convolutional models are trained with a Connectionist Temporal Classification loss and use an explicit language model for decoding, the transformer is a sequence-to-sequence model. Our best performing model improves the state-of-the-art word error rate on the challenging BBC-Oxford Lip Reading Sentences 2 (LRS2) benchmark dataset by over 20 percent. As a further contribution we investigate the fully convolutional model when used for online (real time) lip reading of continuous speech, and show that it achieves high performance with low latency.

Development of sEMG sensors and algorithms for silent speech recognition

Abstract: Objective Speech is among the most natural forms of human communication, thereby offering an attractive modality for human-machine interaction through automatic speech recognition (ASR). However, the limitations of ASR-including degradation in the presence of ambient noise, limited privacy and poor accessibility for those with significant speech disorders-have motivated the need for alternative non-acoustic modalities of subvocal or silent speech recognition (SSR). Approach We have developed a new system of face- and neck-worn sensors and signal processing algorithms that are capable of recognizing silently mouthed words and phrases entirely from the surface electromyographic (sEMG) signals recorded from muscles of the face and neck that are involved in the production of speech. The algorithms were strategically developed by evolving speech recognition models: first for recognizing isolated words by extracting speech-related features from sEMG signals, then for recognizing sequences of words from patterns of sEMG signals using grammar models, and finally for recognizing a vocabulary of previously untrained words using phoneme-based models. The final recognition algorithms were integrated with specially designed multi-point, miniaturized sensors that can be arranged in flexible geometries to record high-fidelity sEMG signal measurements from small articulator muscles of the face and neck. Main results We tested the system of sensors and algorithms during a series of subvocal speech experiments involving more than 1200 phrases generated from a 2200-word vocabulary and achieved an 8.9%-word error rate (91.1% recognition rate), far surpassing previous attempts in the field. Significance These results demonstrate the viability of our system as an alternative modality of communication for a multitude of applications including: persons with speech impairments following a laryngectomy; military personnel requiring hands-free covert communication; or the consumer in need of privacy while speaking on a mobile phone in public.

On the link between error correlation and error reduction in decision tree ensembles

Abstract: Author(s): Ali, Kamal M.; Pazzani, Michael J. | Abstract: Recent work has shown that learning an ensemble consisting of multiple models and then making classifications by combining the classifications of the models often leads to more accurate classifications then those based on a single model learned from the same data. However, the amount of error reduction achieved varies from data set to data set. This paper provides empirical evidence that there is a linear relationship between the degree of error reduction and the degree to which patterns of errors made by individual models are uncorrelated. Ensemble error rate is most reduced in ensembles whose constituents make individual errors in a less correlated manner. The second result of the work is that some of the greatest error reductions occur on domains for which many ties in information gain occur during learning. The third result is that ensembles consisting of models that make errors in a dependent but "negatively correlated" manner will have lower ensemble error rates than ensembles whose constituents make errors in an uncorrelated manner. Previous work has aimed at learning models that make errors in a uncorrelated manner rather than those that make errors in an "negatively correlated" manner. Taken together, these results help provide an understanding of why the multiple models approach yields great error reduction in some domains but little in others.

Sending-or-not-sending twin-field quantum key distribution: Breaking the direct transmission key rate

Abstract: We present improved results of sending-or-not-sending twin-field quantum key distribution by using error rejection through two-way classical communications. Our error rejection method, especially our method of actively odd-parity pairing (AOPP) can drastically improve the performance of sending-or-not-sending twin-field protocol in both secure distance and key rate. Taking a typical experimental parameter setting, our method here improves the secure distance by 70 km to more than 100 km in comparison with the prior art results. Comparative study also shows advantageous in key rates at regime of long distance and large misalignment error rate for our method here. The numerical results show that our method here can significantly exceed the absolute limit of direct transmission key rate, and also have an advantageous key rates higher than various prior art results by 10 to 20 times.