Journal ArticleDOI
Probabilistic-trajectory segmental HMMs☆
TLDR
Performance benefits have been demonstrated from incorporating a linear trajectory description and additionally from modelling variability in the mid-point parameter, and theoretical and experimental comparisons between different types of PTSHMMs, simpler SHMMs and conventional HMMs are presented.About:
This article is published in Computer Speech & Language.The article was published on 1999-01-01. It has received 108 citations till now. The article focuses on the topics: Feature (machine learning) & Hidden Markov model.read more
Citations
More filters
Journal ArticleDOI
Hidden semi-Markov models
TL;DR: An overview of HSMMs is presented, including modelling, inference, estimation, implementation and applications, which has been applied in thirty scientific and engineering areas, including speech recognition/synthesis, human activity recognition/prediction, handwriting recognition, functional MRI brain mapping, and network anomaly detection.
Journal ArticleDOI
Machine Learning Paradigms for Speech Recognition: An Overview
TL;DR: This overview article provides readers with an overview of modern ML techniques as utilized in the current and as relevant to future ASR research and systems, and presents and analyzes recent developments of deep learning and learning with sparse representations.
Reference BookDOI
Speech processing : a dynamic and optimization-oriented approach
Li Deng,Douglas O'Shaughnessy +1 more
TL;DR: Analysis of discrete-time speech signals probability and random processes linear model and dynamic system model optimization methods and estimation theory statistical pattern recognition helps clarify speech technology in selected areas.
Journal ArticleDOI
Speech production knowledge in automatic speech recognition.
TL;DR: A survey of a growing body of work in which representations of speech production are used to improve automatic speech recognition is provided.
Proceedings ArticleDOI
Deformable Markov model templates for time-series pattern matching
Xianping Ge,Padhraic Smyth +1 more
TL;DR: A novel and flexible approach is proposed based on segmental semiMarkov models that provides a systematic and coherent framework for leveraging both prior knowledge and training data for automatically detecting specific patterns or shapes in time-series data.
References
More filters
Journal ArticleDOI
Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences
S. Davis,Paul Mermelstein +1 more
TL;DR: In this article, several parametric representations of the acoustic signal were compared with regard to word recognition performance in a syllable-oriented continuous speech recognition system, and the emphasis was on the ability to retain phonetically significant acoustic information in the face of syntactic and duration variations.
Journal ArticleDOI
Speaker-independent phone recognition using hidden Markov models
Kai-Fu Lee,H.-W. Hon +1 more
TL;DR: The authors introduce the co-occurrence smoothing algorithm, which enables accurate recognition even with very limited training data, and can be used as benchmarks to evaluate future systems.
Journal ArticleDOI
From HMM's to segment models: a unified view of stochastic modeling for speech recognition
TL;DR: A general stochastic model is described that encompasses most of the models proposed in the literature for speech recognition, pointing out similarities in terms of correlation and parameter tying assumptions, and drawing analogies between segment models and HMMs.
Proceedings Article
A word graph algorithm for large vocabulary, continuous speech recognition.
Hermann Ney,Xavier L. Aubert +1 more
TL;DR: In this article, the authors describe a method for the construction of a word graph (or lattice) for large vocabulary, continuous speech recognition, which is obtained as an extension of the one-pass beam search strategy using word dependent copies of the word models or lexical trees.
Journal ArticleDOI
A word graph algorithm for large vocabulary continuous speech recognition
TL;DR: A method for the construction of a word graph (or lattice) for large vocabulary, continuous speech recognition and it is shown that the word graph density can be reduced to an average number of about 10 word hypotheses, per spoken word with virtually no loss in recognition performance.
Related Papers (5)
A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition
Spontaneous speech recognition using a statistical coarticulatory model for the vocal-tract-resonance dynamics.
Li Deng,Jeff Z. Ma +1 more