Speech Recognition Using Deep Neural Networks: A Systematic Review

Abstract

Over the past decades, a tremendous amount of research has been done on the use of machine learning for speech processing applications, especially speech recognition. However, in the past few years, research has focused on utilizing deep learning for speech-related applications. This new area of machine learning has yielded far better results when compared to others in a variety of applications including speech, and thus became a very attractive area of research. This paper provides a thorough examination of the different studies that have been conducted since 2006, when deep learning first arose as a new area of machine learning, for speech applications. A thorough statistical analysis is provided in this review which was conducted by extracting specific information from 174 papers published between the years 2006 and 2018. The results provided in this paper shed light on the trends of research in this area as well as bring focus to new research topics. INDEX TERMS Speech recognition, deep neural network, systematic review.

Emirati-Accented Speaker Identification in Stressful Talking Conditions

“…Furthermore, we intend to involve speakers from the seven emirates of the "UAE (Abu Dhabi, Dubai, Sharjah, Ajman, Umm al-Qaiwain, Ras al-Khaimah, and Fujairah)". Finally, we plan to utilize deep neural networks [22] as classifiers to improve "Emirati-accented speaker identification accuracy in stressful conditions". In addition, our plan is to study and investigate Emirati-accented speaker identification in biased stressful talking environments [23], [24].…”

Directional adversarial training for cost sensitive deep learning classification applications

“…Recent advancements in Deep Learning have lead to several breakthrough applications in many fields, like Computer Vision [24], Health-care [12], Industry 4.0 [29,39], Natural Language Processing [52], Speech Recognition [34] and Transportation [16]. A crucial requirement for many applications in these fields, is to have models that do not have unexpected behaviors.…”

Lithuanian Speech Recognition Using Purely Phonetic Deep Learning

“…Over the years, a large majority of research conducted in this area focused on the most widely spoken languages, such as English, French, Mandarin Chinese, etc. [2,3]. Large corpora of speech data such as Librispeech [4] for English and AISHELL-1 [5] for Mandarin are available.…”