Speaker Identification techniques in Overlapping Speech Analysis: A Review
نویسندگان
چکیده
-This paper addresses the issue of speaker identification in overlapping speech where two speakers are speaking simultaneously over a single communication channel where objective is to find individual speaker identities. This task can be accomplished using feature extraction techniquesbased on which classification model can be developed.This paper studies different feature extraction techniques such as MFCC and GFCC. Also various modeling techniques such as GMM, HMM, SVM, UBM, ANN and DNN are studied. Keywords—Speaker, Identification, supervised, feature extraction. __________________________________________________*****_________________________________________________
منابع مشابه
Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملComprehensive Analysis of Signal Processing Techniques Used For Speaker Identification
Speaker recognition is more active biometric task, which bases from the more general speech processing area. Likewise, most of the other speech-related recognition activities (language recognition, speech recognition), speaker recognition is a multidisciplinary problem. Both understanding of pattern recognition techniques and domain knowledge (Acoustics/Phonetics) are necessary. The motivation ...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Identification in Overlapping Speech
Although the problem of automatic speaker identification has received considerable attention, no work has been made to deal with overlapping speech that involves multiple persons speaking simultaneously. This study proposes two approaches to automatically identify both simultaneous and non-simultaneous speakers in an audio stream. The first approach consists of an overlapping-speech detection c...
متن کاملNovel Approach to Text Independent Speaker Identification
In this paper, we propose Speaker Identification using two transforms, namely Kekre’s Transform and Kekre’s Wavelet Transform. The speech signal is spoken by a particular speaker is converted into a spectrogram by first taking 25 or 50% overlapping frames between consecutive sample vectors and arranged in the form of matrix. In order to improve the performance, intially log of matrix is taken a...
متن کامل