Research Developments and Directions in Speech Recognition and Understanding, Part 1

By Janet M. Baker, Li Deng, James R. Glass, Sanjeev Khudanpur, C. Lee, Nelson Morgan, Douglas O'Shgughnessy. 2009

140 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Deep Learning: Methods and Applications (2014, background): “For example, human speech production and perception systems are both equipped with clearly layered hierarchical structures in transforming the information from the waveform level to the linguistic level [11, 12, 74, 75].”
An Overview of Deep-Structured Learning for Information Processing (2011, background): “For example, human speech production and perception systems are both equipped with clearly layered hierarchical structures in transforming the information from the waveform level to the linguistic level (Baker et al., 2009; Deng, 1999, 2003).”
Large vocabulary continuous speech recognition with context-dependent DBN-HMMS (2011, result): “We hope that the encouraging results we presented in this work will inspire other researchers to investigate related approaches to acoustic modeling in LVCSR, to tackle some of the numerous research challenges deeper acoustic models present, and to provide possible solutions to some of the grand cha”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, unknown): “Despite some success of GMM-HMMs in ASR, their weaknesses , such as the conditional independence assumption, have been well known for ASR applications [1], [30].”
Investigation of full-sequence training of deep belief networks for speech recognition (2010, methodology): “, [1][2][3][5][15][17][18][19][20]), motivated partly by the desire to capitalize on some analogous properties in the human speech generation and perception systems.”
A French Corpus for Distant-Microphone Speech Processing in Real Homes (2016, unknown): “Distant-microphone speaker localization, speech enhancement, and speech recognition remain challenging tasks today [1–6].”
Binary coding of speech spectrograms using a deep auto-encoder (2010, background): “, [1][7]) need to be modified to adapt to the DBN framework, where an additional class-discriminative term in the objective function is needed for training the auto-encoder with the reconstruction of unlabeled data serving the role of regularization.”
Deep Convex Net: A Scalable Architecture for Speech Pattern Classification (2011, methodology): “... type provided by the basic DCN framework presented in this paper; 2) addition of a dynamic programing based decoder on top of the final layer of the DCN to enable continuous phonetic or speech recognition; 3) learning (rather than tuning) of hyper-parameters in DCN; 4) development of speaker and”
Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech Recognition (2010, background): “For example, human speech production and perception systems are both equipped with clearly layered hierarchical structures in transforming the information from the waveform level to the linguistic level in the perception mode and in the opposite direction in the generation mode [24][25].”
A Geometric Perspective of Large-Margin Training of Gaussian Models [Lecture Notes] (2010, background): “The importance of discriminative learning in speech recognition has been elaborated in [ 14 ] and [15].”
An analysis of environment, microphone and data simulation mismatches in robust speech recognition (2017, unknown): “Speech enhancement and automatic speech recognition (ASR) in the presence of reverberation and nonstationary noise are still challenging tasks today (Baker et al., 2009; W¨olfel and McDonough, 2009; Virtanen et al., 2012; Li et al., 2015).”