Litcius/Paper detail

Automatic Speaker Recognition with Limited Data

Ruirui Li, Jyun‐Yu Jiang, Jiahao Liu, Chu-Cheng Hsieh, Wei Wang

202036 citationsDOIOpen Access PDF

Abstract

Automatic speaker recognition (ASR) is a stepping-stone technology towards semantic multimedia understanding and benefits versatile downstream applications. In recent years, neural network-based ASR methods have demonstrated remarkable power to achieve excellent recognition performance with sufficient training data. However, it is impractical to collect sufficient training data for every user, especially for fresh users. Therefore, a large portion of users usually has a very limited number of training instances. As a consequence, the lack of training data prevents ASR systems from accurately learning users acoustic biometrics, jeopardizes the downstream applications, and eventually impairs user experience.

Topics & Concepts

Computer scienceBiometricsSpeaker recognitionDownstream (manufacturing)Training (meteorology)Speech recognitionArtificial neural networkTraining setLabeled dataHuman–computer interactionMultimediaArtificial intelligenceEngineeringMeteorologyPhysicsOperations managementSpeech Recognition and SynthesisMusic and Audio ProcessingSpeech and Audio Processing