The Mixer and Transcript Reading Corpora: Resources for Multilingual, Crosschannel Speaker Recognition Research
作者： Mark Liberman , Christopher Cieri , Mark A. Przybocki , Walter D. Andrews , Shudong Huang
DOI:
关键词:
摘要: Abstract : This paper describes the planning and creation of Mixer Transcript Reading corpora, their properties yields, reports on lessons learned during development.
aclweb.org
brandeis.edu 参考文章(3)
Christopher Cieri, Kevin Walker, David Miller, The Fisher Corpus: a Resource for the Next Generations of Speech-to-Text. language resources and evaluation. ,(2004)
Philip Rose, Technical Forensic Speaker Identification from a Bayesian Linguists Perspective Odyssey 2004 - The Speaker and Language Recognition Workshop. pp. 3- 10 ,(2004)
Douglas A. Reynolds, Joseph P. Campbell, William M. Campbell, Fusing Discriminative and Generative Methods for Speaker Recognition: Experiments on Switchboard and NFI/TNO Field Data Odyssey. pp. 41- 44 ,(2004)