An open/free database and Benchmark for Uyghur speaker recognition
- 1 October 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 81-85
Abstract
Few research has been conducted on Uyghur speaker recognition. Among the limited works, researchers usually collect small speech databases and publish results based on their own private data. This `close-door evaluation' makes most of the publications doubtable. This paper publishes an open and free speech database THUYG-20 SRE and a benchmark for Uyghur speaker recognition. The database is based on the THUYG-20 speech corpus we recently released, and the benchmark involves recognition tasks with various training/enrollment/test conditions. We provide a complete description for the database as well as the benchmark, and present an i-vector baseline system constructed using the Kaldi toolkit.Keywords
This publication has 9 references indexed in Scilit:
- PLDA for speaker verification with utterances of arbitrary duration2013
- Analysis of i-vector length normalization in speaker recognition systems2011
- Discriminatively trained Probabilistic Linear Discriminant Analysis for speaker verification2011
- Simplification and optimization of i-vector extraction2011
- Front-End Factor Analysis for Speaker VerificationIEEE Transactions on Audio, Speech, and Language Processing, 2010
- Probabilistic Linear Discriminant Analysis for Inferences About Identity2007
- Support vector machines for speaker and language recognitionComputer Speech & Language, 2006
- Eigenvoice modeling with sparse training dataIEEE Transactions on Speech and Audio Processing, 2005
- A Tutorial on Text-Independent Speaker VerificationEURASIP Journal on Advances in Signal Processing, 2004