conftrace_

2020 Interspeech INTERSPEECH 2020

VoiceID on the Fly: A Speaker Recognition System that Learns from Scratch

Abstract

We proposed a novel AI framework to conduct real-time multi-speaker recognition without any prior registration or pretraining by learning the speaker identification on the fly. We considered the practical problem of online learning with episodically revealed rewards and introduced a solution based on semi-supervised and self-supervised learning methods in a web-based application at https://www.baihan.nyc/viz/VoiceID/

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

Authors

Baihan Lin, Xinxin Zhang

Topics

Artificial Intelligence > Learning Paradigms > Few-Shot Learning Machine Learning > Learning Types > Self-Supervised Learning Machine Learning > Learning Types > Semi-Supervised Learning Machine Learning > Learning Types > Unsupervised Learning Mathematics & Optimization > Optimization > Online Algorithms

Keywords

semi-supervised learning few-shot learning online learning self-supervised learning speaker recognition multi-speaker recognition

More from Interspeech 2020

All Interspeech 2020 papers →

SoapBox Labs Fluency Assessment Platform for Child Speech

CATOTRON — A Neural Text-to-Speech System in Catalan

Toward Remote Patient Monitoring of Speech, Video, Cognitive and Respiratory Biomarkers Using Multimodal Dialog Technology

Enhancing Transferability of Black-Box Adversarial Attacks via Lifelong Learning for Speech Emotion Recognition Models

End-to-End Speech Emotion Recognition Combined with Acoustic-to-Word ASR Model

Improving Speech Emotion Recognition Using Graph Attentive Bi-Directional Gated Recurrent Unit Network