An overlapping-feature-based phonological model incorporating linguistic constraints: applications to speech recognition.

By Jiping Sun, Li Deng. 2002

85 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, 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 Experimental and Cognitive Psychology

In Signal Processing

Citations in the corpus

Deep Learning: Methods and Applications (2014, background): “One intermediate neural network layer in the implementation of this detection-based framework explicitly represents the speech attributes, which are simplified entities from the “atomic” units of speech developed in the early work of [101, 355].”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “One intermediate neural network layer in the implementation of this detection-based framework explicitly represents the speech attributes, which are simplified entities from the “atomic” units of speech developed in the early work of [136, 137].”
A Bidirectional Target Filtering Model of Speech Coarticulation: two-stage Implementation for Phonetic Recognition (2006, methodology): “More recent work explored the hidden structure of speech associated with various levels in the human speech generation process, either implicitly or explicitly [1], [ 3 ], [6], [8], [14], [22].”
A bidirectional target-filtering model of speech coarticulation and reduction: two-stage implementation for phonetic recognition (2006, unknown): “…the causal physical system in speech articulation that accounts for inertia-related perseverance coarticulation, while the anticipatory coarticulation is modeled at the separate phonological level via the mechanism of nonlinear " atomic unit " overlapping or target look-ahead [8], [29].”
Exploiting deep neural networks for detection-based speech recognition (2013, unknown): “[73]).”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, unknown): “, [130], [237], [238].”
Deep Neural Networks for Acoustic Modeling in Speech Recognition (2012, methodology): “The 22 attributes used in the recent work, as reported in [65], are a subset of the articulatory feature s explored in [66], [67].”
A Deep Neural Network for Acoustic-Articulatory Speech Inversion (2011, methodology): “Systems capable of approximating the position of the articulators from the acoustic signal are useful in several domains: Speech recognition, where articulatory information can improve the performance of the recognition systems [1]; speech synthesis, where it can be used to improve the quality or to”
Updated MINDS Report on Speech Recognition and Understanding, Part 2 (2009, background): “Many phenomena can now be directly and quantifiably observed, such as the time course and details of adaptation and facilitation, semantic dissonance, and so on.”
Deep Belief Networks for phone recognition (2009, background): “Substantial research effo rt has been devoted to going beyond the “beads-on-a-string” view of speech to representing str uctu e in speech above the level of the phonetic segment [5, 6, 7].”
Design and Learning of Output Representations for Speech Recognition (2013, methodology): “Likewise, it has also 101 been well understood for a long time that the use of phonetic or its finer state sequences, even with 102 contextual dependency, in engineering speech recognition systems is inadequate in representing 103 such rich structure [5][12][14][27] and thus leaving a promising open”