Deep-structured hidden conditional random fields for phonetic recognition

By Dong Yu, Li Deng. 2010

45 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

In Signal Processing

Citations in the corpus

Deep Learning: Methods and Applications (2014, methodology): “For example, the deep-structured CRF, which stacks many layers of CRFs, have been usefully applied to the task of language identification [429], phone recognition [410], sequential labeling in natural language processing [428], and confidence calibration in speech recognition [423].”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, methodology): “For example, the deep-structured CRF, which stacks many layers of CRFs, have been successfully used in the task of language identification [103], phone recognition [102], sequential labeling in natural language processing [96], and confidence calibration in speech recognition [178, 179].”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, methodology): “1) Models: When applied to ASR, there are " direct " approaches which use maximum entropy Markov models (MEMMs) [83], conditional random fields (CRFs) [84], [85], hidden CRFs (HCRFs) [71], augmented CRFs [86], segmental CRFs (SCARFs) [72], and deep-structured CRFs [87], [88].”
Investigation of full-sequence training of deep belief networks for speech recognition (2010, background): “Research in speech recognition has explored layered architectures in the recognizer design for quite some time (e.g., [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.”
Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription (2011, methodology): “, [14] uses first and second-order statistics of the observations.”
An Overview of Deep-Structured Learning for Information Processing (2011, methodology): “Various versions of deepstructured CRFs are usefully applied to phone recognition (Yu and Deng, 2010), spoken language identification (Yu, Wang, Karam, and Deng, 2010), and natural language processing (Yu, Wang, and Deng, 2010).”
Binary coding of speech spectrograms using a deep auto-encoder (2010, background): “…has led to renewed interest in exploring deep, multi-layer networks for a number of machine learning problems including encoding [8][9], retrieval [12], as well as the problems associated with classification and regression that involves image [8][9], language [16][17] and speech [10][11][15].”
Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition (2012, methodology): “The idea of using senones as the modeling unit has been proposed in [22] where the posterior probabilities of senones were estimated using deep-structured conditional random ﬁelds (CRFs) and only one audio frame was used as the input of the posterior probability estimator.”
Large vocabulary continuous speech recognition with context-dependent DBN-HMMS (2011, background): “DBN-HMMs are closely related to the artificial neural network (ANN)-HMM hybrid architectures that were first explored as an alternative paradigm for ASR in the late 1980s and early 1990s.”
Deep segmental neural networks for speech recognition (2013, methodology): “A similar deep model to ours has been proposed for the CRF model in [19, 20, 21, 22] with the difference of being frame-based rather than being segment-based.”
Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech Recognition (2010, methodology): “Deep learning techniques have been successfully applied to applications such as natural language processing [12][13], language recognition [14], image processing [15], vision [16], audio encoding [17], audio classification [18], phone recognition [19], and semantic tagging [20] in the last several y”