Language recognition using deep-structured conditional random fields

By Dong Yu, Shizhen Wang, Zahi N. Karam, Li Deng. 2010

46 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): “Over recent years, since the success of the (fully-connected) DNN– HMM hybrid system was demonstrated in [67, 68, 109, 161, 257, 258, 308, 309, 324, 429], many new architectures and nonlinear units have been proposed and evaluated for speech recognition.”
Deep Learning of Representations: Looking Forward (2013, methodology): “With the less common supervised pre-training (Bengio et al., 2007; Yu et al., 2010; Seide et al., 2011b), each additional layer is trained with a supervised objective (as part of a one hidden layer network).”
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].”
Deep-structured hidden conditional random fields for phonetic recognition (2010, methodology): “The proposed MOP-based approach has been shown to be effective in a language identification task involving seven language classes [3].”
An Overview of Deep-Structured Learning for Information Processing (2011, methodology): “For example, the deep-structured CRF, which stacks many layers of CRFs, have been successfully used in the task of language identification (Yu, Wang, Karam, and Deng, 2010), phone recognition (Yu and Deng, 2010)0, sequential labeling in natural language processing (Yu, Wang, and Deng, 2010), and…”
Investigation of full-sequence training of deep belief networks for speech recognition (2010, methodology): “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.,The approach we ”
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”
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].”
Sequential Labeling Using Deep-Structured Conditional Random Fields (2010, methodology): “We have recently proposed techniques to infer the intermediate layers using discriminative criteria [30], [31].”
Learning in the Deep-Structured Conditional Random Fields (2009, methodology): “As an example, we have shown [8][9] that when continuous features are used, better performance can be achieved by imposing constraints on the distribution of the features, which is equivalent to expanding each continuous feature í µí± í µí± í µí±¦ í µí±¡−1 , í µí±¦ í µí±¡ , í µí², í µí±¡ into í…”