We present SpeechStew, a speech recognition model that is trained on a combination of various publicly available speech recognition datasets: AMI, Broadcast News, Common Voice, LibriSpeech, Switchboard/Fisher, Tedlium, and Wall Street Journal. SpeechStew simply mixes all of these datasets together, without any special re-weighting or re-balancing of the datasets. SpeechStew achieves SoTA or near SoTA results across a variety of tasks, without the use of an external language model. Our results include 9.0\% WER on AMI-IHM, 4.7\% WER on Switchboard, 8.3\% WER on CallHome, and 1.3\% on WSJ, which significantly outperforms prior work with strong external language models. We also demonstrate that SpeechStew learns powerful transfer learning representations. We fine-tune SpeechStew on a noisy low resource speech dataset, CHiME-6. We achieve 38.9\% WER without a language model, which compares to 38.6\% WER to a strong HMM baseline with a language model.
翻译:我们推出语音识别模型,这是一个在各种公开的语音识别数据集(AMI、广播新闻、通用语音、LibriSpeech、总机/Fisher、Tedlium和华尔街日报)的组合方面受过培训的语音识别模型,SpeeStew简单将所有这些数据集组合在一起,而不对数据集作任何特别的重新加权或重新平衡。SpeeStew在不使用外部语言模型的情况下,在各种任务中实现SoTA或接近SoTA的结果。我们的成果包括:AMI-IHM的9.0 ⁇ WER,交换机的4.7 ⁇ WER,呼叫Home的8.3 ⁇ WER,以及WSJ的1.3 ⁇,这大大超过以往与强有力的外部语言模型开展的工作。我们还表明,Speereststew学会了强大的传输学习演示。我们微调低资源语音数据集(CHiME-6)上的语音定位Speci-tunSterestStuew on a murry coming lession speal speal-WER,我们实现了38.9 ⁇ 没有语言模型,相比之下比38.6。