Publications Search | Page 2 | SRI International

Toggle Menu

Publications Search

By Vikramjit Mitra, Horacio Franco

The introduction of deep neural networks has significantly improved automatic speech recognition performance.

Sep, 2016
In Proceedings
Topics:
420

This work investigates whether nonlexical information from speech can automatically predict the quality of small-group collaborations.

Sep, 2016
Technical Report
420
By Vikramjit Mitra, Dimitra Vergyri, Horacio Franco

Often, prior knowledge of subword units is unavailable for low-resource languages. Instead, a global subword unit description, such as a universal phone set, is typically used in such scenarios.

Sep, 2016
In Proceedings
Topics:
420

Annotating audio data for the presence and location of speech is a time-consuming and therefore costly task.

Sep, 2016
In Proceedings
Topics:
420

The Speakers in the Wild (SITW) speaker recognition database contains hand-annotated speech samples from open-source media for the purpose of benchmarking text-independent speaker recognition technology on single and multi-speaker audio acquired across unconstrained or “wild” conditions. The...

Sep, 2016
In Proceedings
Topics:
420
By Colleen Richey, Cynthia M. D'Angelo, Nonye M. Alozie, Harry Bratt, Elizabeth Shriberg

(A brief blurb that is used when this item is shown in search results or featured on other pages. Will be cut off after 300 characters when displayed on other pages) We introduce the SRI speech-based collaborative learning corpus, a novel collection designed for the investigation and measurement of...

Sep, 2016
Article
Topics:
420
By Martin Graciarena, Vikramjit Mitra

In this paper, we present the SRI system submission to the NIST OpenSAD 2015 speech activity detection (SAD) evaluation.

Sep, 2016
In Proceedings
Topics:
420

We propose to demonstrate the Open Language Interface for Voice Exploitation (OLIVE) speech-processing system, which SRI International developed under the DARPA Robust Automatic Transcription of Speech (RATS) program. The technology underlying OLIVE was designed to achieve robustness to high levels...

Sep, 2016
In Proceedings
Topics:
420
By Vikramjit Mitra, Andreas Kathol

The rate at which endangered languages can be documented has been highly constrained by human factors.

Sep, 2016
In Proceedings
Topics:
420

Recognizing speech under high levels of channel and/or noise degradation is challenging.

Sep, 2016
In Proceedings
Topics:
420

Pages