Accession Number:

ADA614010

Title:

A Noise-Robust System for NIST 2012 Speaker Recognition Evaluation

Descriptive Note:

Corporate Author:

SRI INTERNATIONAL MENLO PARK CA SPEECH TECHNOLOGY AND RESEARCH LAB

Personal Author(s):

• Ferrer, Luciana
• McLaren, Mitchell
• Scheffer, Nicolas
• Lei, Yun
• Graciarena, Martin
• Mitra, Vikramjit

Report Date:

2013-08-01

Pagination or Media Count:

6.0

Abstract:

The National Institute of Standards and Technology NIST 2012 speaker recognition evaluation posed several new challenges including noisy data, varying test-sample length and number of enrollment samples, and a new metric. Target speakers were known during system development and could be used for model training and score normalization. For the evaluation, SRI International SRI submitted a system consisting of six subsystems that use different low- and high-level features, some specifically designed for noise robustness, fused at the score and iVector levels. This paper presents SRI s submission along with a careful analysis of the approaches that provided gains for this challenging evaluation including a multiclass voice-activity detection system, the use of noisy data in system training, and the fusion of subsystems using acoustic characterization metadata.

Descriptors:

• *SPEECH RECOGNITION
• INFORMATION SYSTEMS
• NOISE
• NORMALIZING(STATISTICS)

Subject Categories:

• Voice Communications

Distribution Statement:

APPROVED FOR PUBLIC RELEASE