arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.04521cs.LG
收藏

语音神经网络的训练方差及性能评估

Training variance and performance evaluation of neural networks in speech

IBM Watson Group(IBM沃森集团)

Ewout van den Berg, Bhuvana Ramabhadran, Michael Picheny

摘要:

在这项工作中,我们研究了自动语音识别中各种配置的神经网络训练结果的方差。虽然这种差异本身是众所周知的,这是,据我们所知,第一篇论文,进行了广泛的实证研究,其影响语音识别。我们将训练视为从分布中采样,并表明这些分布可能具有很大的方差。这些结果表明,迫切需要重新思考的方式,在文献中的结果报告和解释。

英文摘要:

In this work we study variance in the results of neural network training on a wide variety of configurations in automatic speech recognition. Although this variance itself is well known, this is, to the best of our knowledge, the first paper that performs an extensive empirical study on its effects in speech recognition. We view training as sampling from a distribution and show that these distributions can have a substantial variance. These results show the urgent need to rethink the way in which results in the literature are reported and interpreted.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑