Speech Recognition Using Deep Neural Networks: A Systematic Review

By Ali Bou Nassif, Ismail Mohd Adnan Shahin, Imtinan B. Attili, Mohammad Azzeh, Khaled Shaalan. IEEE Access, 2019

947 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/29650544fded20dd5b2fc49f60f9a3ad30d0e275

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Deep Autoencoder based Energy Method for the Bending, Vibration, and Buckling Analysis of Kirchhoff Plates (2020, background): “…variants such as multilayer perceptron (MLP), convolutional neural networks (CNN) and recurrent/recursive neural networks (RNN) [19] have been developed and applied to e.g. image processing [20, 21], object detection [22, 23], speech recognition [24, 25], biology [26, 27] and even ﬁnance [28, 29].”
Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond (2021, background): “While deep learning has been effective in image detection [59], translation [60], speech recognition [61,62], sound synthesis [63] and even automated neural architecture search [64], clinical diagnosis and treatment tasks often need more care (e.g., patient interests, beliefs, social support and…”
A Deep Collocation Method for the Bending Analysis of Kirchhoff Plate (2021, background): “…neural networks (CNN) and recurrent/recursive neural networks (RNN) [16] have been created, which further boost the application of deep learning in image processing [17], object detection [18], speech recognition [19] and many other domains including genomics [20] and even ﬁnance [21].”
Speech Emotion Recognition Using Deep Learning Techniques: A Review (2019, background): “Some applications include dialogue systems for spoken languages such as call center conversations, onboard vehicle driving system and utilization of emotion patterns from the speech in medical applications [7].”
Mel Frequency Cepstral Coefficient and its Applications: A Review (2022, background): “They found that most of the researchers, which was about %69, still use MFCCs as a feature to feed the machine learning models [24].”
Ultra-Low Precision 4-bit Training of Deep Neural Networks (2020, background): “Over the past decade, Deep Neural Networks (DNNs) have surpassed traditional Machine Learning techniques on a wide spectrum of application domains including speech [1–3], computer vision [4–10], and language [11, 12].”
A Survey of Deep Active Learning (2020, background): “ublication of a large number of existing annotation datasets [16, 87], in recent years, DL has made breakthroughs in various fields including machine translation [4, 13, 159, 168], speech recognition [110, 116, 120, 136], and image classification [60, 106, 115, 174]. However, this comes at the cost ”