Mel frequency cepstral coefficients based text independent Automatic Speaker Recognition using matlab

Abstract. The vocal training is useful for beginners to learn how to correctly sing, and for professional singers to tune their voice and expand their frequency range. In the paper, we propose a study on vocal training by analyzing voice pitch on android platform. Vocal training requires a vocal coach who is always besides you to correct your mistakes. However, beginner who wants to learn singing for fun or professional singer who practices his vocal technique everyday rather needs a short-hand assistance to control his or her singing. The proposed method is divided into four parts, such as preprocessing, feature extraction, feature matching and result output, that enables to perform efficient voice recognition. In addition, we describe the various training options of the proposed method, including several statistical analyses in order to describe the user's progress in later stages.

show abstract

“…MFCC is used to determine the pitch of the signal and is calculated using the following equation [4,6]:…”

Section: Proposed Methods Of Analyzing Voice Pitchmentioning

confidence: 99%

A Study on Vocal Training for Beginners by Analyzing Voice Pitch

Park¹,

Nasridinov²,

Byun³

2014

Advanced Science and Technology Letters

View full text Add to dashboard Cite

show abstract

“…For the pattern classification task, widely used techniques are Gaussian mixture modelling [4], vector quantization [5], hidden Markov models [6,7], support vector domain descriptions [8], and types of artificial neural networks [9][10][11]. The most used feature selection techniques in literature are linear predictive analysis methods [12], mel-frequency cepstral coefficients (MFCC) [13,14], and discrete wavelet coefficients (DWTC) [15]. In this work, MFCC features and RBF neural networks are used because of the reported success of RBF in natural signal representation [16,17].…”

Section: Two-stage Decision Making Algorithm For Speaker Verificationmentioning

confidence: 99%

Konuşmaci Doğrulama İçi̇n Eği̇ti̇m Seti̇ Opti̇mi̇zasyonlu İki̇ Aşamali Karar Verme Algori̇tmasi

Yaparoğlu

Şenol

2019

Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi

View full text Add to dashboard Cite

In this paper, a two-stage decision making algorithm is proposed for the task of speaker verification. This twostage algorithm aims to eliminate the first-stage qualifying impostors by the help of impostor-resistant structure in the second stage. First, a baseline system is formed using mel-frequency cepstral coefficients (MFCC) as features and, a radial basis function (RBF) neural network for speaker modelling. Then, the investigations have been realized for optimizing the training set by means of two issues: (1) the ratio of impostor features to genuine speaker features, (2) the ratio of same gender features to opposite gender features (in respect of the genuine speaker) within the impostor speakers' set. Last, the two-stage decision making algorithm is presented, and the performance enhancement provided by the two-stage system is given with the test results.Bu çalışmada, konuşmacı doğrulama görevi için iki aşamalı bir karar verme algoritması önerilmiştir. Bu iki aşamalı algoritma, ikinci aşamada sahtekarlara dayanıklı yapı sayesinde ilk aşamayı geçen sahtekârları ortadan kaldırmayı amaçlıyor. Birinci aşamada, öznitelik olarak mel-frekanslı sepstral katsayılar (MFCC) kullanılarak temel bir sistem oluşturulmuş ve bir radyal taban fonksiyonu (RBF) sinir ağı kullanılarak konuşmacı modellemesi gerçekleştirilmiştir. Ardından, eğitim setini iki kısımda optimize etmek için araştırmalar gerçekleştirildi: (1) taklitçi konuşmacı özniteliklerinin gerçek konuşmacı özniteliklerine oranı, (2) taklitçi konuşmacı kümesi içinde aynı cinsiyet özniteliklerinin zıt cinsiyet özniteliklerine oranı (gerçek konuşmacıya bağlı olarak). Son olarak, iki aşamalı karar verme algoritması sunulmuş ve iki aşamalı sistem tarafından sağlanan performans artışı test sonuçlarıyla birlikte verilmiştir.Anahtar kelimeler: Konuşmacı doğrulama, Eğitim kümesi optimizasyonu, RBF yapay sinir ağları, MFCC, Cohort

show abstract

“…To transform speech signal in frequency domain its very important to make short duration blocks of speech signal of short duration. MFCC is based on the human auditory system [4][5]. The human perception of the frequency contents of sound for speech signals follows a logarithmic scale,called as 'Mel scale' .…”

Section: A Mfcc Processormentioning

confidence: 99%

Speaker Recognition system and it’s Applications

Niwatkar¹,

Kanse²

2019

IJRTE

View full text Add to dashboard Cite

Speaker recognition is the task in which the speaker is identified based on various features from his speech. Speaker recognition is combination of various mathematical operations in which training and testing is the major part. For speaker recognition its very important to extract the features. So far many researches are going on about feature extraction techniques like MFCC, IMFCC etc. In which features can be extracted, but for the exact speaker recognition its very important to get the exact and accurate features so that we can increase the success rate of speaker recognition. For any speaker recognition system feature extraction is the primary and very important step. So the precise result depends on the accurate result of feature extraction technique. In this paper we are proposing a modified feature extraction system.

show abstract

Mel frequency cepstral coefficients based text independent Automatic Speaker Recognition using matlab

Cited by 8 publications

References 2 publications

A Study on Vocal Training for Beginners by Analyzing Voice Pitch

A Study on Vocal Training for Beginners by Analyzing Voice Pitch

Konuşmaci Doğrulama İçi̇n Eği̇ti̇m Seti̇ Opti̇mi̇zasyonlu İki̇ Aşamali Karar Verme Algori̇tmasi

Speaker Recognition system and it’s Applications

Contact Info

Product

Resources

About