Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

York University

$28,000.00

Margin-based discriminative learning of hidden Markov models for speech recognition

FY 2008-09

Summary
In this research program, we will study novel discriminative learning algorithms for automatic speech recognition. They are called discriminative learning because they aim to automatically learn the most relevant information from available training data for the purpose of recognition and classification. Our research will focus on how to define a good criterion for learning and how to use effective optimization methods during learning process in the context of large vocabulary speech recognition. We expect our research work will be equally applicable to other pattern classification tasks as well, such as text categorization, optical character recognition, bioinformatics, computer vision and others.
Program
Discovery Grants Program - Individual
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
261540-2008
Name nom
Jiang, Hui
Department département
Computer Science and Engineering
Organization id
38
Institution établissement
York University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2008
Competition year année de concours
2008
Award amount
28000
Program id
RGPIN
Program nane en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
331
Committee name en
Computing and Information Sciences - B
Committee name fr
Informatique - B
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2801
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Natural language and speech understanding
Research subject fr
Langage naturel et reconnaissance de la parole
Partie
1
Nb partie
5
Application title
Margin-based discriminative learning of hidden Markov models for speech recognition
Keyword
NA
Application summary
In this research program, we will study novel discriminative learning algorithms for automatic speech recognition. They are called discriminative learning because they aim to automatically learn the most relevant information from available training data for the purpose of recognition and classification. Our research will focus on how to define a good criterion for learning and how to use effective optimization methods during learning process in the context of large vocabulary speech recognition. We expect our research work will be equally applicable to other pattern classification tasks as well, such as text categorization, optical character recognition, bioinformatics, computer vision and others.