Open AccessProceedings Article
Speech Recognition using SVMs
ND Smith,Mark J. F. Gales +1 more
- 03 Jan 2001
- Vol. 14, pp 1197-1204
TL;DR: Extensions to a standard scheme for handling variable length data, the Fisher score, are presented and a more useful mapping is introduced based on the likelihood-ratio, which outperforms both the fisher score and HMMs trained to maximise likelihood.
read more
Abstract: An important issue in applying SVMs to speech recognition is the ability to classify variable length sequences. This paper presents extensions to a standard scheme for handling this variable length data, the Fisher score. A more useful mapping is introduced based on the likelihood-ratio. The score-space defined by this mapping avoids some limitations of the Fisher score. Class-conditional generative models are directly incorporated into the definition of the score-space. The mapping, and appropriate normalisation schemes, are evaluated on a speaker-independent isolated letter task where the new mapping outperforms both the Fisher score and HMMs trained to maximise likelihood.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Image Classification with the Fisher Vector: Theory and Practice
Jorge Sánchez,F. Perronnin,Thomas Mensink,Jakob Verbeek +3 more
TL;DR: This work proposes to use the Fisher Kernel framework as an alternative patch encoding strategy: it describes patches by their deviation from an “universal” generative Gaussian mixture model, and reports experimental results showing that the FV framework is a state-of-the-art patch encoding technique.
1.5K
Object detection using feature subset selection
TL;DR: It is argued that feature selection is an important problem in object detection and demonstrated that genetic algorithms (GAs) provide a simple, general, and powerful framework for selecting good subsets of features, leading to improved detection rates.
316
Self-Supervised Speech Representation Learning: A Review
Abdelrahman Mohamed,Hung-yi Lee,Lasse Borgholt,Jakob D. Havtorn,Joakim Edin,Christian Igel,Katrin Kirchhoff,Shang-Wen Li,Karen Livescu,Lars Maaløe,Tara N. Sainath,Shinji Watanabe +11 more
TL;DR: This review presents approaches for self-supervised speech representation learning and their connection to other research areas, and reviews recent efforts on benchmarking learned representations to extend the application beyond speech recognition.
A New Discriminative Kernel From Probabilistic Models
Koji Tsuda,Motoaki Kawanabe,Gunnar Rätsch,Sören Sonnenburg,Klaus-Robert Müller +4 more
- 03 Jan 2001
TL;DR: This work proposes a new discriminative TOP kernel derived from tangent vectors of posterior log-odds and develops a theoretical framework on feature extractors from probabilistic models and uses it for analyzing the TOP kernel.
A review of deep learning techniques for speech processing
TL;DR: A comprehensive overview of the key deep learning models and their applications in speech-processing tasks can be found in this paper , where the authors discuss the challenges and future directions of deep learning in speech processing, including the need for more parameter-efficient, interpretable models and the potential of Deep Learning for multimodal speech processing.
References
•Book
The Nature of Statistical Learning Theory
Vladimir Vapnik
- 01 Jan 1995
TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
46K
Making large scale SVM learning practical
TL;DR: SVM light as discussed by the authors is an implementation of an SVM learner which addresses the problem of large-scale SVM training with many training examples on the shelf, which makes large scale SVM learning more practical.
5K
•Book
Advances in Large Margin Classifiers
Alexander J. Smola,Peter L. Bartlett +1 more
- 01 Oct 2000
TL;DR: This book provides an overview of recent developments in large margin classifiers, examines connections with other methods, and identifies strengths and weaknesses of the method, as well as directions for future research.
1.9K
•Proceedings Article
Exploiting Generative Models in Discriminative Classifiers
Tommi S. Jaakkola,David Haussler +1 more
- 01 Dec 1998
TL;DR: A natural way of achieving this combination by deriving kernel functions for use in discriminative methods such as support vector machines from generative probability models is developed.
•Proceedings Article
Spoken Letter Recognition
Mark Fanty,Ronald A. Cole +1 more
- 01 Oct 1990
TL;DR: This article used a feed-forward neural network classifier to classify spoken letters in a test set of 30 speakers and achieved 95% first choice name retrieval on a database of 50,000 names.
Related Papers (5)
Tommi S. Jaakkola,David Haussler +1 more
- 01 Dec 1998
Vladimir Vapnik
- 01 Jan 1998
Vladimir Vapnik
- 01 Jan 1995