Back to Results
First PageMeta Content
Linguistics / Science / Human–computer interaction / Speech processing / Artificial intelligence applications / Speech recognition / Speaker recognition / Speech synthesis / Loudspeaker / Phonetics / Computational linguistics / Automatic identification and data capture


VOICE CONVERGIN: SPEAKER DE-IDENTIFICATION BY VOICE TRANSFORMATION Qin Jin, Arthur R. Toth, Tanja Schultz, Alan W Black Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA ABSTRACT Spea
Add to Reading List

Document Date: 2009-05-04 17:09:33


Open Document

File Size: 377,21 KB

Share Result on Facebook

Company

SLM / BASELINE SYSTEMS / /

Currency

USD / /

Facility

Carnegie Mellon University / Alan W Black Language Technologies Institute / /

IndustryTerm

feature processing / telephone-based banking services / bank / speaker recognition systems / voice-based access systems / speaker verification systems / obvious solution / Automatic speaker recognition systems / natural language processing / identification systems / null-grammar network / signal processing artifacts / /

MusicAlbum

Speech / /

Organization

Black Language Technologies Institute / American Medical Informatics Association / Carnegie Mellon University / Pittsburgh / /

Person

Phonetic Model / Arthur R. Toth / VOICE CONVERGIN / Identification / Alan W Black / Qin Jin / Verification / Tanja Schultz / /

/

Position

ABSTRACT Speaker / Language-dependent Speaker / corresponding original speaker / target speaker / the baseline strategy / original speaker / source speaker / same speaker / Gaussian Mixture Speaker / target speaker / SPEAKER / original target speaker / Text-independent Speaker / Far-field Speaker / estimated target speaker / source and target speaker / /

Product

Phonetic SID system / Phonetic SID / /

ProvinceOrState

Vermont / Pennsylvania / /

Technology

speech recognition / VT technologies / natural language processing / WSOLA algorithm / EM algorithm / /

URL

http /

SocialTag