2020 · 104 citations · 30 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingDeep LearningNeural NetworksPattern RecognitionSpeech RecognitionSpiking Neural NetworksEncoder-decoder ArchitecturesEnd-to-end Speech RecognitionIntegrate-and-fire ModelsTransductionWord Error Rate
In this paper, we propose a novel soft and monotonic alignment mechanism used for sequence transduction. It is inspired by the integrate-and-fire model in spiking neural networks and employed in the encoder-decoder framework consists of continuous functions, thus being named as: Continuous Integrate-and-Fire (CIF). Applied to the ASR task, CIF not only shows a concise calculation, but also supports online recognition and acoustic boundary positioning, thus suitable for various ASR scenarios. Several support strategies are also proposed to alleviate the unique problems of CIF-based model. With the joint action of these methods, the CIF-based model shows competitive performance. Notably, it achieves a word error rate (WER) of 2.86% on the test-clean of Librispeech and creates new state-of-the-art result on Mandarin telephone ASR benchmark.
30
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Martı́n Abadi, Ashish Agarwal, Paul Barham et al. · arXiv (Cornell University) · 2016 · 9.8K citations · Full text
Librispeech: An ASR corpus based on public domain audio books
Vassil Panayotov, Guoguo Chen, Daniel Povey et al. · 2015 · 6K citations
Computing, Computer Science, English +17
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Daniel Park, William Chan, Yu Zhang et al. · 2019 · 3.5K citations · Full text
Attention-Based Models for Speech Recognition
Jan Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk et al. · arXiv (Cornell University) · 2015 · 1.8K citations · Full text