SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

Daniel S. Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D. Cubuk, Quoc V. Le
<span title="2019-07-23">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. We apply SpecAugment on Listen, Attend and Spell networks for end-to-end speech recognition tasks. We achieve state-of-the-art performance on the LibriSpeech 960h and Swichboard
more &raquo; ... 0h tasks, outperforming all prior work. On LibriSpeech, we achieve 6.8% WER on test-other without the use of a language model, and 5.8% WER with shallow fusion with a language model. This compares to the previous state-of-the-art hybrid system of 7.5% WER. For Switchboard, we achieve 7.2%/14.6% on the Switchboard/CallHome portion of the Hub5'00 test set without the use of a language model, and 6.8%/14.1% with shallow fusion, which compares to the previous state-of-the-art hybrid system at 8.3%/17.3% WER.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.08779v2">arXiv:1904.08779v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ay2xqzwsgbgtbi2hydlxfk7gza">fatcat:ay2xqzwsgbgtbi2hydlxfk7gza</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200830111655/https://arxiv.org/pdf/1904.08779v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/31/13/3113358e7219787f5d8b15b319976a273045720b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.08779v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>