2019 NIST Speaker Recognition Evaluation Test Set -- Audio-Visual
| Item Name: | 2019 NIST Speaker Recognition Evaluation Test Set -- Audio-Visual |
| Author(s): | Omid Sadjadi, Craig Greenberg, Xuansong Li, Stephanie Strassel |
| LDC Catalog No.: | LDC2023V01 |
| ISLRN: | 470-750-139-731-6 |
| DOI: | https://doi.org/10.35111/pqkt-6r56 |
| Release Date: | February 15, 2023 |
| Member Year(s): | 2023 |
| DCMI Type(s): | MovingImage, Text |
| Sample Type: | mp4 |
| Sample Rate: | 44100 |
| Data Source(s): | web collection |
| Project(s): | NIST SRE, VAST |
| Application(s): | speaker identification |
| Language(s): | English |
| Language ID(s): | eng |
| License(s): |
LDC User Agreement for Non-Members |
| Online Documentation: | LDC2023V01 Documents |
| Licensing Instructions: | Subscription & Standard Members, and Non-Members |
| Citation: | Sadjadi, Omid, et al. 2019 NIST Speaker Recognition Evaluation Test Set -- Audio-Visual LDC2023V01. Web Download. Philadelphia: Linguistic Data Consortium, 2023. |
| Related Works: | View |
Introduction
2019 NIST Speaker Recognition Evaluation Test Set -- Audio-Visual was developed by the Linguistic Data Consortium (LDC) and NIST (National Institute of Standards and Technology). It contains approximately 64 hours of English audio-visual data for development and test, answer keys, enrollment, trial files and documentation from the NIST-sponsored 2019 Speaker Recognition Evaluation (SRE).
The ongoing series of SRE yearly evaluations conducted by NIST are intended to be of interest to researchers working on the general problem of text independent speaker recognition. To this end the evaluations are designed to be simple, to focus on core technology issues, to be fully supported and to be accessible to those wishing to participate.
The 2019 evaluation task was speaker detection, that is, to determine whether a specified target speaker was speaking during a segment of speech. The evaluation was conducted in two parts: (1) a leaderboard-style challenge based on conversational telephone speech from LDC's Call My Net 2 corpus; and (2) a separate evaluation using audio-visual data collected by LDC for the VAST (Video Annotation for Speech Technology) project. Further information about the 2019 evaluation is contained in the evaluation plan included in this release.
Data
The VAST collection focused on amateur video recordings from various online media hosting services. The recordings vary in duration from 17.5 seconds to 13 minutes.
Videos are encoded/compressed as mp4 files. Audio tracks are in aac format with a sample rate of 44.1 KHz; most have two audio channels (stereo), but some are monophonic (one channel).
Samples
Please view these samples:
Updates
None at this time.