Text Independent Speaker Identification for Myanmar Speech
Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering · 2019
Nowadays, speech signal processing is one of the emerg ing applicat ion areas of d igital processing.There are many research areas related to speech processing such as speaker recognition, speech recognition, and speech synthesis.Speaker identificat ion is the task of analy zing the speakers' characteristics in speech to exactly identify individuals.The identification task perfo rms better when there is enough background training data.Mel Frequency Cepstral Coefficient (MFCC), Perceptual Linear Pred iction (PLP) and Filter Bank features are extracted as front-end processing.Constructing Universal Background Model (UBM) is the main co mponent of i-vector system as it is essential for collecting statistics from speech utterances and for clustering the speaker models.Th is paper indicates that the impacts of unlimited speech data in speaker identification by using i-vector method with probabilistic linear discriminative analysis (PLDA) approach and the import role of speaker models in identification process.