4 months ago
GTM-UVigo Systems for the Query-by-Example Search on Speech Task at MediaEval 2015
GTM-UVigo Systems for the Query-by-Example Search on Speech Task at MediaEval 2015
{Carmen Garcia-Mateo Laura Docio-Fernandez Paula Lopez-Otero}
Abstract
In this paper, we present the systems developed by GTMUVigo team for the query by example search on speech task (QUESST) at MediaEval 2015. The systems consist in a fusion of 11 dynamic time warping based systems that use phoneme posteriorgrams for speech representation; the primary system introduces a technique to select the most relevant phonetic units on each phoneme decoder, leading to an improvement of the search results.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| keyword-spotting-on-quesst | GTM-UVigo Contrastive (eval) | Cnxe: 0.999 MinCnxe: 0.923 lowerbound : 0.633 |
| keyword-spotting-on-quesst | GTM-UVigo Contrastive (dev) | Cnxe: 0.998 MinCnxe: 0.918 lowerbound : 0.635 |
| keyword-spotting-on-quesst | GTM-UVigo Primary late submission (eval) | Cnxe: 0.871 MinCnxe: 0.838 lowerbound : 0.592 |
| keyword-spotting-on-quesst | GTM-UVigo Contrastive late submission (dev) | Cnxe: 0.907 MinCnxe: 0.864 lowerbound : 0.618 |
| keyword-spotting-on-quesst | GTM-UVigo Contrastive late submission (eval) | Cnxe: 0.989 MinCnxe: 0.852 lowerbound : 0.613 |
| keyword-spotting-on-quesst | GTM-UVigo Primary (eval) | Cnxe: 0.919 MinCnxe: 0.905 lowerbound : 0.629 |
| keyword-spotting-on-quesst | GTM-UVigo Primary (dev) | Cnxe: 0.917 MinCnxe: 0.905 lowerbound : 0.627 |
| keyword-spotting-on-quesst | GTM-UVigo Primary late submission (dev) | Cnxe: 0.875 MinCnxe: 0.847 lowerbound : 0.593 |
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