Production models as a structural basis for automatic speech recognition

By Li Deng, Gordon Ramsay, Don X. Sun. 1997

How researchers see this paper

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

1. Li Deng
2. Dong Yu
3. Xiao Li
4. A. Acero
5. Li Deng
6. Jinyu Li
7. Yoshua Bengio
8. Abdel-rahman Mohamed

Citations in the corpus

• Deep Learning: Methods and Applications (2014, background): “It is important to note that the unique elasticity of temporal dynamics of speech as elaborated in (Deng et al., 1997; Bridle et al., 1998; Deng, 1998, 2006) would require temporally-correlated”
• A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “Subsequent work added a new hidden layer into the dynamic model so as to explicitly account for the target-directed, articulatory-like properties in human speech generation [15, 16, 67–73].”
• Switching Dynamic System Models for Speech Articulation and Acoustics (2004, methodology): “We refer the readers to some earlier work for ways of constructing such over­ lapping units, either by rules or by automatic learning, which have proved effective in the HMM-like speech recognition framework [21, 19, 18 , 56] .”
• Structured speech modeling (2006, methodology): “Various simplified implementations of the aforementioned generic nonlinear system model have appeared in the literature (e.g., [4], [15], [17], [20], [24], [26], [37]).”
• Machine Learning Paradigms for Speech Recognition: An Overview (2013, methodology): “There have been several studies on switching nonlinear state space models for ASR, both theoretical [39], [49] and experimental [41]–[43], [50].”
• Computational Models for Speech Production (2018, background): “They differ from each other by distinct objects of dynamic modeling, one at the level of biomechanic articulators (body space) and the other at the level of more abstract task variables (task space) 6 [1, 2, 9, 4, 5, 25].”
• A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition (1998, unknown): “Second, the articulatory dynamic or stochastic target model aims at accounting for detailed movement behavior of biomechanical articulators guided by the multi-dimensional target distributions de®ned in the biomechanical articulator coordinate space [25] [26] [62].”
• Dynamic Speech Models: Theory, Algorithms, and Applications (2006, background): “This particular proposal for using the joint articulatory, acoustic, and auditory properties to specify the articulatory control in the domain of articulatory parameters was originally proposed in [59, 78].”