Performance comparison of speaker recognition systems using GMM and i-Vector methods with PNCC and RASTA PLP features

Nayana, P. K.; Mathew, Dominic; Abraham, Thomas

doi:10.1109/icicict1.2017.8342603

Cited by 9 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Relative Spectra Perceptual Linear Prediction (RASTA-PLP) is based on the human auditory system's ability which would be insensitive to slowly changing proper-ties. It is inspired by RASTA filter [14]. In PLP Coefficient extraction steps, RASTA filtering is used as a band pass filter to suppress the slowly changing components.…”

Section: Methodsmentioning

confidence: 99%

Bilingual Speech Emotion Recognition Using Neural Networks: A Case Study for Turkish and English Languages

Ozsonmez

Acarman

Parlak

2021

Intelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation

View full text Add to dashboard Cite

Emotion extraction and detection are considered as complex tasks due to the nature of data and subjects involved in the acquisition of sentiments. Speech analysis becomes a critical gateway in deep learning where the acoustic features would be trained to obtain more accurate descriptors to disentangle sentiments, customs in natural language. Speech feature extraction varies by the quality of audio records and linguistic properties. The speech nature is handled through a broad spectrum of emotions regarding the age, the gender and the social effects of subjects. Speech emotion analysis is fostered in English and German languages through multilevel corpus. The emotion features disseminate the acoustic analysis in videos or texts. In this study, we propose a multilingual analysis of emotion extraction using Turkish and English languages. MFCC (Mel-Frequency Cepstrum Coefficients), Mel Spectrogram, Linear Predictive Coding (LPC) and PLP-RASTA techniques are used to extract acoustic features. Three different data sets are analyzed using feed forward neural network hierarchy. Different emotion states such as happy, calm, sad and angry are compared in bilingual speech records. The accuracy and precision metrics are reached at level higher than 80%. Turkish language emotion classification is concluded to be more accurate regarding speech features.

show abstract

Section: Methodsmentioning

confidence: 99%

Bilingual Speech Emotion Recognition Using Neural Networks: A Case Study for Turkish and English Languages

Ozsonmez

Acarman

Parlak

2021

Intelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation

View full text Add to dashboard Cite

show abstract

“…The basic idea of the i-vector based speaker recognition system is that assume both the speaker information and channel information are contained in the GMM's high-dimensional mean super-vector space, in this super-vector space, by training the Total Variability (TV) space which contains speaker information and the channel difference to decompose super-vector S of each speaker's speech data into Equation (1) [13].…”

Section: The Principle Of I-vectormentioning

confidence: 99%

Text independent voiceprint recognition model based on I-vector

Zhang¹,

Yao²

2020

IJATEE

View full text Add to dashboard Cite

Speaker Recognition is a technology for identifying people based on the Voiceprint characteristics contained in voice, and is a kind of biometric authentication technology. According to different recognition methods, Voiceprint recognition can be divided into three categories [1]. (1) Speaker discrimination is to distinguish who is talking from a given speaker set; (2) speaker confirmation is to judge whether someone is speaking or not; (3) speaker segmenting and clustering is to distinguish the switching time of different speakers based on the voice formed by multiple speakers.

show abstract

A New Text Independent Speaker Recognition System with Short Utterances Using SVM

Chakroun

Frikha

2020

Information Systems

View full text Add to dashboard Cite

Performance comparison of speaker recognition systems using GMM and i-Vector methods with PNCC and RASTA PLP features

Cited by 9 publications

References 7 publications

Bilingual Speech Emotion Recognition Using Neural Networks: A Case Study for Turkish and English Languages

Bilingual Speech Emotion Recognition Using Neural Networks: A Case Study for Turkish and English Languages

Text independent voiceprint recognition model based on I-vector

A New Text Independent Speaker Recognition System with Short Utterances Using SVM

Contact Info

Product

Resources

About