A Denoising Autoencoder for Speaker Recognition. Results on the MCE 2018 Challenge
| Autor: | Roberto Font |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Denoising autoencoder
Computer science Speech recognition Pipeline (computing) 020206 networking & telecommunications 02 engineering and technology Speaker recognition Set (abstract data type) 030507 speech-language pathology & audiology 03 medical and health sciences Identification (information) Discriminative model 0202 electrical engineering electronic engineering information engineering 0305 other medical science |
| Zdroj: | ICASSP |
| DOI: | 10.1109/icassp.2019.8683525 |
| Popis: | We propose a Denoising Autoencoder (DAE) for speaker recognition, trained to map each individual ivector to the mean of all ivectors belonging to that particular speaker. The aim of this DAE is to compensate for inter-session variability and increase the discriminative power of the ivectors prior to PLDA scoring. We test the proposed approach on the MCE 2018 1st Multi-target speaker detection and identification Challenge Evaluation. This evaluation presents a call-center fraud detection scenario: given a speech segment, detect if it belongs to any of the speakers in a blacklist. We show that our DAE system consistently outperforms the usual LDA + PLDA pipeline, achieving a Top-S EER of 4.33% and Top-1 EER of 6.11% on the evaluation set, which represents a 45.6% error reduction with respect to the baseline system provided by organizers. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|