Speaker recognition based on idiolectal differences between speakers. Doddington, G. R In Eurospeech 2001. Proceedings of the 7th European Conference on Speech Communication and Technology, 2nd Interspeech Event, pages 2521-2524, Aalborg, Denmark, September 3-7, 2001.
Speaker recognition based on idiolectal differences between speakers [link]Paper  abstract   bibtex   
Familiar speaker information is explored using non-acoustic features in NIST's new extended data speaker detection task. Word unigrams and bigrams, used in a traditional target/background likelihood ratio framework, are shown to give surprisingly good performance. Performance continues to improve with additional training and/or test data. Bigram performance is also found to be a function of target/model sex and age difference. These initial experiments strongly suggest that further exploration of familiar speaker characteristics will likely be an extremely interesting and valuable research direction for recognition of speakers in conversational speech.
@inproceedings{doddington_speaker_2001,
	Address = {Aalborg, Denmark, September 3-7, 2001},
	Author = {Doddington, George R},
	Booktitle = {Eurospeech 2001. Proceedings of the 7th European Conference on Speech Communication and Technology, 2nd Interspeech Event},
	Date = {2001},
	Date-Modified = {2016-09-24 18:56:02 +0000},
	File = {Attachment:files/3105/Doddington - 2001 - Speaker recognition based on idiolectal differences between speakers.pdf:application/pdf},
	Keywords = {speaker recognition, speech technology},
	Pages = {2521-2524},
	Title = {Speaker recognition based on idiolectal differences between speakers},
	Url = {http://www.isca-speech.org/archive/eurospeech_2001/e01_2521.html http://www.isca-speech.org/archive/eurospeech_2001/e01_2521.html},
	Abstract = {Familiar speaker information is explored using non-acoustic features in NIST's new extended data speaker detection task. Word unigrams and bigrams, used in a traditional target/background likelihood ratio framework, are shown to give surprisingly good performance. Performance continues to improve with additional training and/or test data. Bigram performance is also found to be a function of target/model sex and age difference. These initial experiments strongly suggest that further exploration of familiar speaker characteristics will likely be an extremely interesting and valuable research direction for recognition of speakers in conversational speech.},
	Bdsk-File-1 = {YnBsaXN0MDDUAQIDBAUGJCVYJHZlcnNpb25YJG9iamVjdHNZJGFyY2hpdmVyVCR0b3ASAAGGoKgHCBMUFRYaIVUkbnVsbNMJCgsMDxJXTlMua2V5c1pOUy5vYmplY3RzViRjbGFzc6INDoACgAOiEBGABIAFgAdccmVsYXRpdmVQYXRoWWFsaWFzRGF0YV8QXy4uLy4uLy4uL0JpYmxpb2dyYWZpYS9QYXBlcnMvRG9kZGluZ3Rvbi9TcGVha2VyIHJlY29nbml0aW9uIGJhc2VkIG9uIGlkaW9sZWN0YWwgZGlmZmVyZW5jZXMucGRm0hcLGBlXTlMuZGF0YU8RAlQAAAAAAlQAAgAADE1hY2ludG9zaCBIRAAAAAAAAAAAAAAAAAAAAMv2H85IKwAAEIZqaB9TcGVha2VyIHJlY29nbml0aW8jMTA4NjZBNkEucGRmAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQhmpq1AnTMAAAAAAAAAAAAAMABAAACSAAAAAAAAAAAAAAAAAAAAAKRG9kZGluZ3RvbgAQAAgAAMv2A64AAAARAAgAANQJtxAAAAABABQQhmpoEIZljgAF/EcABfuYAADARgACAGhNYWNpbnRvc2ggSEQ6VXNlcnM6AGpvYXF1aW1fbGxpc3RlcnJpOgBCaWJsaW9ncmFmaWE6AFBhcGVyczoARG9kZGluZ3RvbjoAU3BlYWtlciByZWNvZ25pdGlvIzEwODY2QTZBLnBkZgAOAHAANwBTAHAAZQBhAGsAZQByACAAcgBlAGMAbwBnAG4AaQB0AGkAbwBuACAAYgBhAHMAZQBkACAAbwBuACAAaQBkAGkAbwBsAGUAYwB0AGEAbAAgAGQAaQBmAGYAZQByAGUAbgBjAGUAcwAuAHAAZABmAA8AGgAMAE0AYQBjAGkAbgB0AG8AcwBoACAASABEABIAblVzZXJzL2pvYXF1aW1fbGxpc3RlcnJpL0JpYmxpb2dyYWZpYS9QYXBlcnMvRG9kZGluZ3Rvbi9TcGVha2VyIHJlY29nbml0aW9uIGJhc2VkIG9uIGlkaW9sZWN0YWwgZGlmZmVyZW5jZXMucGRmABMAAS8AABUAAgAY//8AAIAG0hscHR5aJGNsYXNzbmFtZVgkY2xhc3Nlc11OU011dGFibGVEYXRhox0fIFZOU0RhdGFYTlNPYmplY3TSGxwiI1xOU0RpY3Rpb25hcnmiIiBfEA9OU0tleWVkQXJjaGl2ZXLRJidUcm9vdIABAAgAEQAaACMALQAyADcAQABGAE0AVQBgAGcAagBsAG4AcQBzAHUAdwCEAI4A8AD1AP0DVQNXA1wDZwNwA34DggOJA5IDlwOkA6cDuQO8A8EAAAAAAAACAQAAAAAAAAAoAAAAAAAAAAAAAAAAAAADww==},
	Bdsk-Url-1 = {http://www.isca-speech.org/archive/eurospeech_2001/e01_2521.html%20http://www.isca-speech.org/archive/eurospeech_2001/e01_2521.html}}
Downloads: 0