Back to Results
First PageMeta Content
Human communication / Automatic identification and data capture / Speech processing / Linguistics / Computer accessibility / Speaker recognition / Speaker diarisation / Surround sound / Voice activity detection / Speech recognition / Computational linguistics / Human–computer interaction


Crowd++: Unsupervised Speaker Count with Smartphones Chenren Xu† , Sugang Li† , Gang Liu§ , Yanyong Zhang† Emiliano Miluzzo∗ , Yih-Farn Chen∗ , Jun Li† , Bernhard Firner† WINLAB, Rutgers University, North
Add to Reading List

Document Date: 2013-09-27 16:15:00

Open Document

File Size: 368,13 KB

Share Result on Facebook

City

Chan / Acoustic / Zurich / /

Company

Application-Based Systems / HTC / Markel / Samsung / Tarzia S. P. / AT&T Labs / College-Hill Press / Rosenberg A. E. / Google / Prentice-Hall Inc. / Venkatagiri S. P. / Springer-Verlag New York Inc. / /

Country

Switzerland / United States / /

Currency

USD / /

/

Facility

Most Crowded Restaurant / Shopping Mall / Rutgers University / University of Texas / /

IndustryTerm

multipitch tracking algorithm / speech processing methods / backend server / food courts / personal social diary applications / noise-resilient pitch estimation algorithm / speech processing community / speech processing algorithms / android devices / dedicated external hardware / energy / energy-based methods / energy consumption / generalized residual radio algorithm / audio data processing / feasible solution / smartphone audio inference applications / geo-fencing technologies / machine learning algorithm / speech processing / human networks / ambient audio energy / energy efficiency / audio inference applications / machine learning algorithms / unsupervised learning algorithm / ad-hoc hardware / audio processing applications / energy-based algorithms / pitch estimation algorithm / Rasta processing / speaker count algorithm / radio devices / external hardware / smartphone context-aware applications / time-domain pitch calculation algorithm / telephone conversations / radio equipment / social sensing applications / forward clustering algorithm / pitch estimation algorithms / /

Movie

A. D. / Hung / /

OperatingSystem

Microsoft Windows / Android / /

Organization

Rutgers University / etc / Center for Robust Speech Systems / Food Court / Acoustical Society of America / University of Texas at Dallas / /

Person

Sensing / Sciarrone / Jun Li / Schriberg / Bernhard Firner / Different / Roy Choudhury / Gang Liu / Emiliano Miluzzo / Cj / Distinguishing Features / Sha / /

/

Position

Estimated Speaker / utterance Same speaker / chair movement / Public Indoor Environments Speaker / single speaker / A. Speaker / General / Outdoor Environments Speaker / same speaker / Human Factors Author / Existing Speaker / E. Speaker / Speaker / O. Speaker / MOTIVATION AND CHALLENGES Speaker / previously inferred speaker / teacher / Some speaker / pocket Speaker / /

Product

Galaxy Tab / a system called Crowd+ / Samsung Samsung Google Google / HTC Evo 4G Smartphone / Galaxy S2 phone / Galaxy S2 / Crowd+ / /

ProgrammingLanguage

Java / C / /

ProvinceOrState

Texas / A. B. / /

Technology

pitch estimation algorithms / geo-fencing technologies / mobile phones / unsupervised learning algorithm / mobile devices / encryption / Java / counting algorithm / multipitch tracking algorithm / bluetooth / energy-based algorithms / pitch estimation algorithm / speech recognition / machine learning algorithms / machine learning algorithm / smartphone / speaker count algorithm / speech processing algorithms / machine learning / Android / mobile device / generalized residual radio algorithm / time-domain pitch calculation algorithm / noise-resilient pitch estimation algorithm / forward clustering algorithm / cellular telephone / Smartphones / /

SocialTag