Litcius/Paper detail

Robust Text-independent Speaker recognition with Short Utterances using Gaussian Mixture Models

Rania Chakroun, Mondher Frikha

202017 citationsDOI

Abstract

An important amount of speech is typically required for speaker identification system development and evaluation. Nowadays, robust speaker identification systems when short utterances are used remains a key consideration for automatic speaker recognition, since a lot of real world applications are able to deal with only limited duration speech data. This paper presents a new approach based on a low complexity solution based on a new feature vectors to build Gaussian Mixture Models (GMM) for speaker identification systems especially when training and testing utterance lengths are reduced. We compared our proposed system to the state-of-the-art based system in Speaker identification. Experiments on TIMIT database were conducted to demonstrate that this new feature vector can outperform the standard GMM-based system and show that there is no need for extra-data to identify the speakers.

Topics & Concepts

Computer scienceSpeech recognitionMixture modelSpeaker recognitionSpeaker identificationUtteranceTIMITFeature (linguistics)Speaker diarisationIdentification (biology)Artificial intelligenceGaussianFeature vectorPattern recognition (psychology)Hidden Markov modelBiologyPhilosophyLinguisticsPhysicsQuantum mechanicsBotanySpeech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing