4 months ago
ELiRF at MediaEval 2015: Query by Example Search on Speech Task (QUESST)
ELiRF at MediaEval 2015: Query by Example Search on Speech Task (QUESST)
{Emilio Sanchis Lluís-F. Hurtado Marcos Calvo Sergio Laguna}
Abstract
n this paper, we present the systems that the Natural Language Engineering and Pattern Recognition group (ELiRF) has submitted to the MediaEval 2015 Query by Example Search on Speech Task. All of them are based on a Subsequence Dynamic Time Warping algorithm. The systems use information from outside the task (low-resources systems).
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| keyword-spotting-on-quesst | ELiRF SDTW (dev) | ATWV: 0.1404 Cnxe: 1.0701 MTWV: 0.1493 MinCnxe: 0.8702 |
| keyword-spotting-on-quesst | ELiRF SDTW-avg (dev) | ATWV: 0.1446 Cnxe: 1.0651 MTWV: 0.1543 MinCnxe: 0.8677 |
| keyword-spotting-on-quesst | ELiRF SDTW-avg (eval) | ATWV: 0.1125 Cnxe: 1.0731 MTWV: 0.1181 MinCnxe: 0.8751 |
| keyword-spotting-on-quesst | ELiRF SDTW (eval) | ATWV: 0.0449 Cnxe: 1.1879 MTWV: 0.0581 MinCnxe: 0.9338 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.
AI Co-coding
Ready-to-use GPUs
Best Pricing
Hyper Newsletters
Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp