Title: Collaborated feature supervector and collaborated language model for phonotactic language recognition

Authors: Wei-Wei Liu; Guo-Chun Li; Cun-Xue Zhang; Tai-Qing Dong; Jian-Hua Zhou; Yan-Miao Song; Jian-Zhong Liu; Zhao Peng; Yu-Bin Huang; Jian-Feng Tong; Jing-Fang Lu; Xing-Hua He; Yu-Jian Tang; Fu-Qiang Yuan; Bin Guo; Lei Gao

Addresses: Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China ' Department of Electronic Engineering, Tsinghua University, Beijing 100084, China

Abstract: The now-acknowledged vulnerabilities of phonotactic language recognition (PLR) technology to long-term contexts have spawned interests to develop many methods to overcome it. In this paper an approach to build a collaborated feature supervector (CFS) built with binary decision tree feature and N-gram feature is proposed, and a collaborated language model (CLM) is introduced, which used to applied to deal with the problems of phonotactic language identification tasks, such as weak to handling long-term contexts and an exponential growth of the number of the parameters in the processing of modelling. Experiments are carried out on the database of National Institute of Standards and Technology Language Recognition Evaluation 2009 (NIST LRE 2009). The experimental results have confirmed that phonotactic language recognition system using the collaborated language model yields 1.07%, 2.68%, 13.48% in equal error rate (EER), which means 8.54%, 12.70% and 4.60% relative reduction for 30 s, 10 s, 3 s compared to the baseline system, respectively.

Keywords: collaborated feature supervector; CFS; collaborated language model; CLM; phonotactic language recognition.

DOI: 10.1504/IJHI.2019.106787

International Journal of Hybrid Intelligence, 2019 Vol.1 No.4, pp.269 - 283

Received: 02 Jan 2019
Accepted: 21 Mar 2019
Published online: 20 Apr 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article