A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic Knowledge. (29th November 2016)

• Record Type: Journal Article
• Authors: Smirnov, Valentin; Ignatov, Dmitry; Gusev, Michael; Farkhadov, Mais; Rumyantseva, Natalia; Farkhadova, Mukhabbat
• Other Names: Karpov Alexey Academic Editor.
• Is Part Of: Journal of electrical and computer engineering. Volume 2016(2016)
• Publication Date: 2016-11-29
• Subjects: Computer engineering -- Periodicals; Electrical engineering -- Periodicals; 621.3905
• DOI: 10.1155/2016/4062786
• Languages: English
• ISSNs: 2090-0147

Abstract

Abstract : The paper describes the key concepts of a word spotting system for Russian based on large vocabulary continuous speech recognition. Key algorithms and system settings are described, including the pronunciation variation algorithm, and the experimental results on the real-life telecom data are provided. The description of system architecture and the user interface is provided. The system is based on CMU Sphinx open-source speech recognition platform and on the linguistic models and algorithms developed by Speech Drive LLC. The effective combination of baseline statistic methods, real-world training data, and the intensive use of linguistic knowledge led to a quality result applicable to industrial use.