Large vocabulary continuous speech recognition with context-dependent DBN-HMMS

By George E. Dahl, Dong Yu, Li Deng, A. Acero. 2011

202 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Speech & Audio, 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

In Speech & Audio

In Signal Processing

Citations in the corpus

Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin (2015, background): “pe of convolution was ﬁrst proposed for neural networks in speech more than 25 years ago [67]. Many neural network speech models have a ﬁrst layer that processes input frames with some context window [16, 66]. This can be viewed as a temporal convolution with a stride of one. Additionally, sub-sampl”
Listen, attend and spell: A neural network for large vocabulary conversational speech recognition (2015, background): “ntroduction Deep Neural Networks (DNNs) have led to improvements in various components of speech recognizers. They are commonly used in hybrid DNN-HMM speech recognition systems for acoustic modeling [1, 2, 3, 4, 5, 6]. DNNs have also produced signiﬁcant gains in pronunciation models that map words ”
Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition (2017, methodology): “Kaldi [23] is a toolkit for speech recognition that is used to train a context-dependent LDA-MLLT-GMM-HMM system.”
Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval (2015, positive): “This work has been motivated by the earlier successes of deep learning methods in speech (Dahl et al., 2011; Yu & Deng, 2011; Dahl et al., 2012; Hinton et al., 2012; Deng et al., 2012) and in semantic modeling (Huang et al.”
Feature Learning in Deep Neural Networks - A Study on Speech Recognition Tasks (2013, methodology): “Because the temporal structure of the HMM is maintained, we refer to these models as CD-DNN-HMM acoustic models.”
A Primal-Dual Method for Training Recurrent Neural Networks Constrained by the Echo-State Property (2013, methodology): “…paper, we build a “deep” version of the RNN by using an independent DNN to extract high-level features from the raw speech data, capitalizing on the well established evidence for the power of DNNs in carrying out automatic feature extraction (Hinton et al., 2012; Dahl et al., 2011; LeCun, 2012).”
A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion (2013, methodology): “extraction and recognition, scaling very well from small [8][26][27][28] to medium [3][4][19][36] and to large [2][6][17]”
Advances in all-neural speech recognition (2016, methodology): “In the recent renaissance of neural network speech recognit ion [1, 2, 3, 4, 5], as well as in pioneering earlier work [6, 7], the netw orks have been mainly used as a drop-in replacement for the acoust i model in an HMM system.”
Recurrent Neural Networks for Noise Reduction in Robust ASR (2012, unknown): “Robust automatic speech recognition (ASR), that with background noise and channel distortion, is a fundamental problem as ASR increasingly moves to mobile devices.”
Convolutional Neural Networks for Speech Recognition (2014, background): “The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Haizhou Li.”
Small-footprint keyword spotting using deep neural networks (2014, methodology): “For our baseline HMM system, as in previous work [8, 9, 17] the labels in the output layer of the neural network are contextdependent HMM states.”
Pruning deep neural networks by optimal brain damage (2014, background): “Recent studies demonstrate that deep neural networks (DNN) are much more powerful than conventional Gaussian mixture models (GMM) in acoustic modeling for automatic speech recognition(ASR) [1, 2, 3].”