Speaker recognition using weighted dynamic MFCC based on GMM

Weng, Zufeng; Li, Lin; Guo, Donghui

doi:10.1109/icasid.2010.5551341

Cited by 20 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When an audio signal is converted in matrix data set with the help of MFCC output then this MFCC output works as a input for classifier model. There are multiple models used by different researchers for speaker recognition like "Gaussian Mixture Model" (GMM) [14] [15][16] [17], "Hidden Markov Model" (HMM) [18], "Support Vector Machine" (SVM) [19]…”

Section: = ∑ ( )mentioning

confidence: 99%

Improved Speaker Recognition for Degraded Human Voice using Modified-MFCC and LPC with CNN

Moondra¹,

Chahal²

2023

IJACSA

View full text Add to dashboard Cite

Economical speaker recognition solution from degraded human voice signal is still a challenge. This article is covering results of an experiment which targets to improve feature extraction method for effective speaker identification from degraded human audio signal with the help of data science. Every speaker's audio has identical characteristics. Human ears can easily identify these different audio characteristics and classify speaker from speaker's audio. Mel-Frequency Cepstral Coefficient (MFCC) supports to get same intelligence in machine also. MFCC is extensively used for human voice feature extraction. In our experiment we have effectively used MFCC and Linear Predictive Coding (LPC) for better speaker recognition accuracy. MFCC first outlines frames and then finds cepstral coefficient for each frame. MFCC use human audio signal and convert it in numerical value of audio features, which is used to recognize speaker efficiently by Artificial Intelligence (AI) based speaker recognition system. This article covers how effectively audio features can be extracted from degraded human voice signal. In our experiment we have observed improved Equal Error Rate (EER) and True Match Rate (TMR) due to high sampling rate and low frequency range for mel-scale triangular filter. This article also covers pre-emphasis effects on speaker recognition when high background noise comes with audio signal.

show abstract

Section: = ∑ ( )mentioning

confidence: 99%

Improved Speaker Recognition for Degraded Human Voice using Modified-MFCC and LPC with CNN

Moondra¹,

Chahal²

2023

IJACSA

View full text Add to dashboard Cite

show abstract

“…The extraction algorithm was an improved algorithm base on the MFCC coefficient extraction algorithm [6]. Firstly, the speech signal would be pretreated, which included pre-emphasis, Front-end detection, framing and windowed.…”

Section: B Auditory Feature Extraction Based On Gammatonementioning

confidence: 99%

A New Algorithm for Auditory Feature Extraction

Lin

Sun

et al. 2012

2012 International Conference on Communication Systems and Network Technologies

View full text Add to dashboard Cite

The human auditory system possesses remarkable capabilities to analyze and identify signals. An auditory feature can improve the performance of speaker recognition system. In this paper, it used gammatone filter to model auditory system, and extracted a traditional auditory feature based on logarithmic energy. On the purpose to reduce the dimension of the traditional auditory feature which was always a highdimensional feature, we took use of discrete cosine transform (DCT). Therefore, it was feasible to apply auditory model extracted in a new way to speech feature extraction. The experiments showed that the GFCC feature, which was extracted in the new method, performed better than t he traditional MFCC feature in the speaker recognition system based on GMM model.

show abstract

“…In the studies [16] and [17], MFCC features were employed in speaker verification systems using i-vector and GMM classifiers respectively. The study [18], employed MFCC features and GMM to develop a speaker recognition system. In the studies [19], [20] speaker recognition systems using the GMM and MFCC features were proposed as the biometrics for smart home device control and remote identification over the voice-over-internet protocol (VoIP) respectively.…”

Section: Introductionmentioning

confidence: 99%

Speaker identification under noisy conditions using hybrid convolutional neural network and gated recurrent unit

Anito,

Srinivasagan,

Jifara

et al. 2024

IJ-AI

View full text Add to dashboard Cite

Speaker identification is biometrics that classifies or identifies a person from other speakers based on speech characteristics. Recently, deep learning models outperformed conventional machine learning models in speaker identification. Spectrograms of the speech have been used as input in deep learning-based speaker identification using clean speech. However, the performance of speaker identification systems gets degraded under noisy conditions. Cochleograms have shown better results than spectrograms in deep learning-based speaker recognition under noisy and mismatched conditions. Moreover, hybrid convolutional neural network (CNN) and recurrent neural network (RNN) variants have shown better performance than CNN or RNN variants in recent studies. However, there is no attempt conducted to use a hybrid CNN and enhanced RNN variants in speaker identification using cochleogram input to enhance the performance under noisy and mismatched conditions. In this study, a speaker identification using hybrid CNN and the gated recurrent unit (GRU) is proposed for noisy conditions using cochleogram input. VoxCeleb1 audio dataset with real-world noises, white Gaussian noises (WGN) and without additive noises were employed for experiments. The experiment results and the comparison with existing works show that the proposed model performs better than other models in this study and existing works.

show abstract

Speaker recognition using weighted dynamic MFCC based on GMM

Cited by 20 publications

References 11 publications

Improved Speaker Recognition for Degraded Human Voice using Modified-MFCC and LPC with CNN

Improved Speaker Recognition for Degraded Human Voice using Modified-MFCC and LPC with CNN

A New Algorithm for Auditory Feature Extraction

Speaker identification under noisy conditions using hybrid convolutional neural network and gated recurrent unit

Contact Info

Product

Resources

About