Phonetic Search Methods for Large Speech Databases

• Κύριοι συγγραφείς: Moyal, Ami (Συγγραφέας), Aharonson, Vered (Συγγραφέας), Tetariy, Ella (Συγγραφέας), Gishri, Michal (Συγγραφέας)
• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: New York, NY : Springer New York : Imprint: Springer, 2013.
• Σειρά: SpringerBriefs in Electrical and Computer Engineering,
• Θέματα: Engineering.; Computational linguistics.; Signal, Image and Speech Processing.; Language Translation and Linguistics.; Computational Linguistics.

“Phonetic Search Methods for Large Databases” focuses on Keyword Spotting (KWS) within large speech databases. The brief will begin by outlining the challenges associated with Keyword Spotting within large speech databases using dynamic keyword vocabularies. It will then continue by highlighting the...

Πίνακας περιεχομένων:

• Keyword Spotting out of Continuous Speech
• Introduction
• Problem Formulation: KWS in Large Speech Databases
• Target Applications of Keyword Spotting
• Keyword Spotting Methods
• LVCSR-Based KWS
• Acoustic KWS
• Phonetic Search KWS
• Discussion: Why Phonetic Search?
• Response Time
• KWS Performance
• Keyword Flexibility
• Phonetic Search
• The Search Mechanism
• Using Phonetic Search for KWS
• Computational Complexity Analysis
• Search Space Complexity Reduction
• Overview
• Complexity Reduction in Phonetic Search
• Anchor-based Phonetic Search
• Evaluating Phonetic Search KWS
• Performance Metrics
• Evaluation Process
• Evaluation Databases
• Evaluation Results
• Exhaustive Search. - Textual Benchmark
• KWS on Speech
• Anchor-based Search
• Textual Benchmark
• Reduced Complexity KWS on Speech
• Multiple Thresholds
• Lessons Learned from the Evaluation
• Summary
• Glossary of Acronyms
• References.