摘要翻译：
近年来的研究表明，在大词汇量的语音识别任务中，深度神经网络（DNNs）明显优于浅层网络和高斯混合模型（GMMs）。在本文中，我们认为DNNs所取得的提高精度是由于它们能够提取对语音信号中的多种变异性来源具有鲁棒性的鉴别性内部表征。我们发现，随着网络深度的增加，这些表示对输入中的小扰动变得越来越不敏感，这导致了更深网络的更好的语音识别性能。我们还表明DNNs不能外推到与训练样本本质不同的测试样本。然而，如果训练数据具有足够的代表性，那么由DNN学习的内部特征相对于说话人差异、带宽差异和环境失真是相对稳定的。这使得基于DNN的识别器能够在不需要显式模型自适应或特征归一化的情况下，执行与基于GMM或浅层网络的现有系统相同或更好的性能。
---
英文标题：
《Feature Learning in Deep Neural Networks - Studies on Speech Recognition
  Tasks》
---
作者：
Dong Yu, Michael L. Seltzer, Jinyu Li, Jui-Ting Huang, Frank Seide
---
最新提交年份：
2013
---
分类信息：

一级分类：Computer Science        计算机科学
二级分类：Machine Learning        机器学习
分类描述：Papers on all aspects of machine learning research (supervised, unsupervised, reinforcement learning, bandit problems, and so on) including also robustness, explanation, fairness, and methodology. cs.LG is also an appropriate primary category for applications of machine learning methods.
关于机器学习研究的所有方面的论文（有监督的，无监督的，强化学习，强盗问题，等等），包括健壮性，解释性，公平性和方法论。对于机器学习方法的应用，CS.LG也是一个合适的主要类别。
--
一级分类：Computer Science        计算机科学
二级分类：Computation and Language        计算与语言
分类描述：Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.
涵盖自然语言处理。大致包括ACM科目I.2.7类的材料。请注意，人工语言（编程语言、逻辑学、形式系统）的工作，如果没有明确地解决广义的自然语言问题（自然语言处理、计算语言学、语音、文本检索等），就不适合这个领域。
--
一级分类：Computer Science        计算机科学
二级分类：Neural and Evolutionary Computing        神经与进化计算
分类描述：Covers neural networks, connectionism, genetic algorithms, artificial life, adaptive behavior. Roughly includes some material in ACM Subject Class C.1.3, I.2.6, I.5.
涵盖神经网络，连接主义，遗传算法，人工生命，自适应行为。大致包括ACM学科类C.1.3、I.2.6、I.5中的一些材料。
--
一级分类：Electrical Engineering and Systems Science        电气工程与系统科学
二级分类：Audio and Speech Processing        音频和语音处理
分类描述：Theory and methods for processing signals representing audio, speech, and language, and their applications. This includes analysis, synthesis, enhancement, transformation, classification and interpretation of such signals as well as the design, development, and evaluation of associated signal processing systems. Machine learning and pattern analysis applied to any of the above areas is also welcome.  Specific topics of interest include: auditory modeling and hearing aids; acoustic beamforming and source localization; classification of acoustic scenes; speaker separation; active noise control and echo cancellation; enhancement; de-reverberation; bioacoustics; music signals analysis, synthesis and modification; music information retrieval;  audio for multimedia and joint audio-video processing; spoken and written language modeling, segmentation, tagging, parsing, understanding, and translation; text mining; speech production, perception, and psychoacoustics; speech analysis, synthesis, and perceptual modeling and coding; robust speech recognition; speaker recognition and characterization; deep learning, online learning, and graphical models applied to speech, audio, and language signals; and implementation aspects ranging from system architecture to fast algorithms.
处理代表音频、语音和语言的信号的理论和方法及其应用。这包括分析、合成、增强、转换、分类和解释这些信号，以及相关信号处理系统的设计、开发和评估。机器学习和模式分析应用于上述任何领域也是受欢迎的。感兴趣的具体主题包括：听觉建模和助听器；声波束形成与声源定位；声场景分类；说话人分离；有源噪声控制和回声消除；增强；去混响；生物声学；音乐信号的分析、合成与修饰；音乐信息检索；多媒体音频和联合音视频处理；口语和书面语建模、切分、标注、句法分析、理解和翻译；文本挖掘；言语产生、感知和心理声学；语音分析、合成、感知建模和编码；鲁棒语音识别；说话人识别与特征描述；应用于语音、音频和语言信号的深度学习、在线学习和图形模型；以及从系统架构到快速算法的实现方面。
--

---
英文摘要：
  Recent studies have shown that deep neural networks (DNNs) perform significantly better than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech recognition tasks. In this paper, we argue that the improved accuracy achieved by the DNNs is the result of their ability to extract discriminative internal representations that are robust to the many sources of variability in speech signals. We show that these representations become increasingly insensitive to small perturbations in the input with increasing network depth, which leads to better speech recognition performance with deeper networks. We also show that DNNs cannot extrapolate to test samples that are substantially different from the training examples. If the training data are sufficiently representative, however, internal features learned by the DNN are relatively stable with respect to speaker differences, bandwidth differences, and environment distortion. This enables DNN-based recognizers to perform as well or better than state-of-the-art systems based on GMMs or shallow networks without the need for explicit model adaptation or feature normalization.
---
PDF链接：
https://arxiv.org/pdf/1301.3605