Fuzzy vector quantization for speaker recognition under limited data conditions

被引：0

作者：

Jayanna, H. S. ^{[1
]}

Prasanna, S. R. Mahadeva ^{[1
]}

机构：

[1] Indian Inst Technol Guwahati, Dept Elect & Commun Engn, Gauhati 781039, India

来源：

2008 IEEE REGION 10 CONFERENCE: TENCON 2008, VOLS 1-4 | 2008年

关键词：

speaker recognition; limited data; DTM; CVQ and FVQ;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This work focuses on the task of speaker recognition under limited data conditions. In case of limited data, the amount of available training and testing data will be few seconds. Under such conditions the conventional classifiers will have very few feature vectors for modelling. This work performs an experimental evaluation of three simple modelling techniques namely, Direct Template Matching (DTM), Crisp Vector Quantization (CVQ) and Fuzzy Vector Quantization (FVQ). Among these FVQ shows significant improved performance compared to DTM and CVQ. For about 3 s of training and testing data the performance for DTM, CVQ and FVQ are 76.67, 73.33, and 86.67, respectively, for a set of first 30 speakers taken from the WHO database.

引用

页码：124 / 127

页数：4

共 50 条

[21] A Fuzzy Neuro Clustering Based Vector Quantization for Face Recognition
Varghese, Elizabeth B.
Wilscy, M.
[J]. ADVANCES IN COMPUTING AND COMMUNICATIONS, PT III, 2011, 192 : 383 - 395
[22] Speaker identification based on vector quantization
Radová, V
Svenda, Z
[J]. TEXT, SPEECH AND DIALOGUE, 1999, 1692 : 341 - 344
[23] Fuzzy Learning Vector Quantization Approaches for Interval Data
de Menezes e Silva Filho, Telmo
Souza, Renata M. C. R.
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ - IEEE 2013), 2013,
[24] Comparison of Generative and Discriminative Approaches for Speaker Recognition with Limited Data
Silovsky, Jan
Cerva, Petr
Zdansky, Jindrich
[J]. RADIOENGINEERING, 2009, 18 (03) : 307 - 316
[25] An investigation on speaker vector-based speaker identification under noisy conditions
Goto, Yuki
Akatsu, Tatsuya
Katoh, Masaharu
Kosaka, Tetsuo
Kohda, Masaki
[J]. 2008 INTERNATIONAL CONFERENCE ON AUDIO, LANGUAGE AND IMAGE PROCESSING, VOLS 1 AND 2, PROCEEDINGS, 2008, : 1430 - 1435
[26] Limited Labels for Unlimited Data: Active Learning for Speaker Recognition
Shum, Stephen H.
Dehak, Najim
Glass, James R.
[J]. 15TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2014), VOLS 1-4, 2014, : 383 - 387
[27] Text-constrained Speaker Verification using Fuzzy C Means Vector Quantization
Saswati, Debnath
Badal, Soni
Das Pradip, K.
[J]. 2015 INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND SIGNAL PROCESSING (ICCSP), 2015, : 1511 - 1515
[28] Automatic Speaker Recognition :An Approach using DWT based Feature Extraction and Vector Quantization
Singhai, Jyoti
Singhai, Rakesh
[J]. IETE TECHNICAL REVIEW, 2007, 24 (05) : 395 - 402
[29] Automatic speaker recognition : An approach using DWT based feature extraction and vector quantization
Singhai, Jyoti
Singhai, Rakesh
[J]. IETE Technical Review (Institution of Electronics and Telecommunication Engineers, India), 2007, 24 (05): : 395 - 402
[30] Speaker Recognition For Digital Forensic Audio Analysis Using Learning Vector Quantization Method
Manurung, Danny Bastian
Dirgantoro, Burhanuddin
Setianingsih, Casi
[J]. 2018 IEEE INTERNATIONAL CONFERENCE ON INTERNET OF THINGS AND INTELLIGENCE SYSTEM (IOTAIS), 2018, : 221 - 226

← 1 2 3 4 5 →