StorEbook: How Goldilocks and the Three Bears is Driving Text-to-Speech Technology
processing techniques and output to your speakers. Mishra believes that something TTS researchers ... , will not capture the quirks and mannerisms of a particular speaker, quirks and ma

StorEBook: How Goldilocks and the Three Bears is Driving Text-to-Speech Technology
to your speakers. Mishra believes that something TTS researchers call prominence will play ... and mannerisms of a particular speaker, quirks and mannerisms that give each one of our v

Distinguished Speaker: Hackers and Inventors
false Pablos Holman, hackers, futurist Pablos Holman Pablos Holman, a computer hacker with no formal education (also an inventor and technology futurist), will discuss invention projects under way at

Why net neutrality is a bad idea
Florham Park Auditorium, reception following false net neutality, distinguished speaker Jon Crowcroft Jon Crowcroft is the Marconi Professor of Communications Systems in the Computer Lab, at th

Enhanced Indexing and Representation with Vision-Based Biometrics
Leveraging visual biometrics for indexing and representations of content for retrieval and verification.

Video - Analytics and Indexing
A background on analytics and indexing (i.e. metadata), their production, and use. Links to projects within the AT&T Video and Multimedia Technologies and Research Department.

Crowd++: unsupervised speaker count with smartphones
Crowd++: Unsupervised Speaker Count with Smartphones Chenren Xu†, Sugang Li†, Gang Liu§, Yanyong ... Audio Inference, Smartphone Sensing, Speaker Count INTRODUCTION The most direct

From Speaker Identification to Affective Analysis:

A Multi-Step System for Analyzing Children Stories
From Speaker Identification to Affective Analysis: A Multi-Step System for Analyzing Children ... to iden- tify candidate characters and attribute each quote to the most likely speaker

Unsupervised speaker segmentation of multi-speaker speech data
Systems and methods for unsupervised segmentation of multi-speaker speech or audio data by speaker ... is initially segmented and then clustered into groups of segments that correspond

Unsupervised Speaker Segmentation Of Multi-Speaker Speech Data
Systems and methods for unsupervised segmentation of multi-speaker speech or audio data by speaker ... is initially segmented and then clustered into groups of segments that correspond