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
••
18 Jul 2018TL;DR: This paper shows how Hierarchical Multitask Learning can encourage the formation of useful intermediate representations by performing Connectionist Temporal Classification at different levels of the network with targets of different granularity.
Abstract: In Automatic Speech Recognition, it is still challenging to learn useful intermediate representations when using high-level (or abstract) target units such as words. For that reason, when only a few hundreds of hours of training data are available, character or phoneme-based systems tend to outperform word-based systems. In this paper, we show how Hierarchical Multitask Learning can encourage the formation of useful intermediate representations. We achieve this by performing Connectionist Temporal Classification at different levels of the network with targets of different granularity. Our model thus performs predictions in multiple scales for the same input. On the standard 300h Switchboard training setup, our hierarchical multitask architecture demonstrates improvements over singletask architectures with the same number of parameters. Our model obtains 14.0% Word Error Rate on the Switchboard subset of the Eval2000 test set without any decoder or language model, outperforming the current state-of-the-art on non-autoregressive Acoustic-to-Word models.
64 citations
•
19 Mar 1990TL;DR: In this article, the framing bit errors of a received digital communications signal are monitored and recorded and an audible alarm is sounded when the error rate exceeds a predetermined threshold value in a plurality of calculation modes.
Abstract: The framing bit errors of a received digital communications signal are monitored and recorded. The framing bit error rate is determined and an audible alarm is sounded when the error rate exceeds a predetermined threshold value in a plurality of calculation modes. The framing bit error rate and the total framing bit errors detected over a predetermined fixed time period is also displayed. A link to a remote network monitor can be implemented for monitoring and displaying framing bit error rate at a remote location.
64 citations
••
01 Dec 2014TL;DR: It is shown that it is possible to learn an efficient acoustic model using only a small amount of easily available word-level similarity annotations, and the resulting model is shown to perform much better than raw speech features in an ABX minimal-pair discrimination task.
Abstract: We show that it is possible to learn an efficient acoustic model using only a small amount of easily available word-level similarity annotations. In contrast to the detailed phonetic labeling required by classical speech recognition technologies, the only information our method requires are pairs of speech excerpts which are known to be similar (same word) and pairs of speech excerpts which are known to be different (different words). An acoustic model is obtained by training shallow and deep neural networks, using an architecture and a cost function well-adapted to the nature of the provided information. The resulting model is evaluated in an ABX minimal-pair discrimination task and is shown to perform much better (11.8% ABX error rate) than raw speech features (19.6%), not far from a fully supervised baseline (best neural network: 9.2%, HMM-GMM: 11%).
64 citations
••
IBM1
TL;DR: These models are feedforward networks with the property that the unfolded layers which correspond to the recurrent layer have time-shifted inputs and tied weight matrices and can be implemented efficiently through matrix-matrix operations on GPU architectures which makes it scalable for large tasks.
Abstract: We introduce recurrent neural networks (RNNs) for acoustic modeling which are unfolded in time for a fixed number of time steps. The proposed models are feedforward networks with the property that the unfolded layers which correspond to the recurrent layer have time-shifted inputs and tied weight matrices. Besides the temporal depth due to unfolding, hierarchical processing depth is added by means of several non-recurrent hidden layers inserted between the unfolded layers and the output layer. The training of these models: (a) has a complexity that is comparable to deep neural networks (DNNs) with the same number of layers; (b) can be done on frame-randomized minibatches; (c) can be implemented efficiently through matrix-matrix operations on GPU architectures which makes it scalable for large tasks. Experimental results on the Switchboard 300 hours English conversational telephony task show a 5% relative improvement in word error rate over state-of-the-art DNNs trained on FMLLR features with i-vector speaker adaptation and hessianfree sequence discriminative training. Index Terms: recurrent neural networks, speech recognition
64 citations
•
01 Jun 2008TL;DR: This work presents the first English syllabification system to improve the accuracy of letter-tophoneme conversion and proposes a novel discriminative approach to automatic syllabization based on structured SVMs.
Abstract: We present the first English syllabification system to improve the accuracy of letter-tophoneme conversion. We propose a novel discriminative approach to automatic syllabification based on structured SVMs. In comparison with a state-of-the-art syllabification system, we reduce the syllabification word error rate for English by 33%. Our approach also performs well on other languages, comparing favorably with published results on German and Dutch.
64 citations