A recent area of significant progress in speaker recognition is the use of high level features—idiolect, phonetic relations, prosody, discourse structure, etc. A speaker not on...
William M. Campbell, Joseph P. Campbell, Douglas A...
Support vector machines (SVMs) have proven to be a powerful technique for pattern classification. SVMs map inputs into a high dimensional space and then separate classes with a hy...
William M. Campbell, Joseph P. Campbell, Douglas A...
Many tasks in speech processing involve classification of long term characteristics of a speech segment such as language, speaker, dialect, or topic. A natural technique for dete...
This work presents a new approach to discriminative speaker verification. Rather than estimating speaker models, or a model that discriminates between a speaker class and the cla...
This paper extends our previous work on feature transformationbased support vector machines for speaker recognition by proposing a joint MAP adaptation of feature transformation (...