Machine Learning Paradigms for Speech Recognition: An Overview

By Li Deng, Xiao Li. 2013

413 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

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

1. Li Deng
2. Dong Yu
3. Jinyu Li
4. Jianfeng Gao
5. Yoshua Bengio
6. Mohit Bansal
7. Kyunghyun Cho
8. Percy Liang

In Signal Processing

1. Dong Yu
2. Li Deng
3. Jinyu Li
4. Yifan Gong
5. Yoshua Bengio
6. M. Seltzer
7. Chin-Hui Lee
8. Ossama Abdel-Hamid

Citations in the corpus

• Deep Learning: Methods and Applications (2014, background): “, Chapter 28 in [264], and Reference [95], it may be natural to just classify deep learning techniques into deep discriminative models (e.”
• A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “…state-space formulation of the RNN model above but in a generative mode, known as the hidden dynamic model as briefly discussed in Section III-A, speech recognition researchers have built many types of speech recognizers over the past 20 some years; see a survey in Sections III-D and III-E of [34].”
• Deep Reinforcement Learning (2018, background): “performs RNNs over a wide range of tasks. SeeJurafsky and Martin(2017),Goldberg(2017),Deng and Liu(2018) for books on NLP; Hirschberg and Manning(2015);Cho(2015);Young et al.(2017) for surveys on NLP;Deng and Li (2013);Gao et al.(2018a);Hinton et al.(2012);He and Deng(2013);Young et al.(2013) for su”
• Discriminative template learning in group-convolutional networks for invariant speech representations (2015, background): “Speech recognition systems built with statistical learning algorithms rely on the pre-assumption that the unknown probability distribution of speech data is fixed or similar for both train and test sets [1, 2].”
• A Review on Automatic Speech Recognition Architecture and Approaches (2016, background): “The generative component is mostly exploited to help with discrimination as the final goal of the hybrid architecture [16][17][18].”
• Transfer learning for speech and language processing (2015, background): “Machine learning (ML) techniques have been extensively exploited in modern speech and language processing research [1], [2], [3].”
• A novel pyramidal-FSMN architecture with lattice-free MMI for speech recognition (2018, methodology): “I, RNNLM 1. INTRODUCTION Deep neural networks (DNN) have been applied as acoustic model (AM) on large vocabulary continuous speech recognition (LVCSR) system in recent years other than GMM-HMM models [1, 2]. Early works such as feedforward neural networks (FNN) [3] only takes current time steps as i”
• A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, background): “In the case of human-human dialogues, an ideal corpus should closely resemble natural dialogues between humans.”
• Deep Reinforcement Learning: An Overview (2017, background): “See a survey paper on applying machine learning to speech recognition (Deng and Li, 2013).”
• Recent advances in deep learning for speech research at Microsoft (2013, background): “However, given the very nature of multitask machine learning (as reviewed in [11]), multilingual speech recognition is best suited for”
• Spoken Language Recognition: From Fundamentals to Practice (2013, methodology): “[78] X.”
• Convolutional Neural Networks for Speech Recognition (2014, background): “Gaussian mixture models (GMMs) have been, until very recently, regarded as the most powerful model Manuscript received October 11, 2013; revised February 04, 2014; accepted July 05, 2014.”
• Hierarchical Bayesian combination of plug-in maximum a posteriori decoders in deep neural networks-based speech recognition and speaker adaptation (2017, background): “Automatic speech recognition (ASR) can be regarded as a sequential pattern classification problem due to the dynamic nature of the speech signal (Deng and Li, 2013).”