The 2013 BBN Vietnamese telephone speech keyword spotting system

Author

Tsakalidis, Stavros ; Hsiao, Ruey-Chang ; Karakos, Damianos ; Ng, Timothy ; Ranjan, Sudhir ; Saikumar, Guruprasad ; Le Zhang ; Nguyen, L. ; Schwartz, R. ; Makhoul, John

Author_Institution

Raytheon BBN Technol., Cambridge, MA, USA

fYear

2014

fDate

4-9 May 2014

Firstpage

7829

Lastpage

7833

Abstract

In this paper we describe the Vietnamese conversational telephone speech keyword spotting system under the IARPA Babel program for the 2013 evaluation conducted by NIST. The system contains several, recently developed, novel methods that significantly improve speech-to-text and keyword spotting performance such as stacked bottleneck neural network features, white listing, score normalization, and improvements on semi-supervised training methods. These methods resulted in the highest performance for the official IARPA Babel surprise language evaluation of 2013.

Keywords

speech recognition; telephone sets; IARPA Babel surprise language evaluation; NIST; Vietnamese conversational telephone speech keyword spotting system; score normalization; semi-supervised training methods; speech-to-text; stacked bottleneck neural network features; white listing; Acoustics; Adaptation models; Hidden Markov models; Lattices; Speech; Speech recognition; Training; keyword spotting; score normalization; stacked bottleneck neural network features; white listing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on

Conference_Location

Florence

Type

conf

DOI

10.1109/ICASSP.2014.6855124

Filename

6855124