An MFCC‐based text‐independent speaker identification system for access control

Liu, Jung-Chun; Leu, Fang-Yie; Lin, Guan-Liang; Susanto, Heru

doi:10.1002/cpe.4255

Cited by 37 publications

(18 citation statements)

References 25 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Text-independent recognition is the much more challenging of the two tasks [3]. Moreover, in real life, text-independent systems are more commercially attractive than text-dependent systems because it is harder to mimic an unknown phrase than a known one [5] In this work, we focus on text-independent of speaker recognition, which can be roughly divided into two parts: speaker identification and speaker verification [6]. These two subfields have a bit varied in definition from domain usage.…”

Section: Introductionmentioning

confidence: 99%

“…The classical Mel-frequency cepstral coefficients (MFCCs) method is likely the most popular feature extraction strategy used to date [6] for audio and speech signal. From literature, most of the state-of-the-art speaker identification systems use MFCC as feature extractor, and then feed these features to GMM-based approaches for creating speaker models for identification [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Text-Independent Speaker Identification Using Deep Learning Model of Convolution Neural Network

Bunrit¹,

Inkian²,

Kerdprasop³

et al. 2019

IJMLC

View full text Add to dashboard Cite

Speaker recognition approach can be categorized into speaker identification and speaker verification. These two subfields have a bit varied in definition from domain usage. If we has a voice input, the goal of speaker verification is for authentication by determining an answer from a question: "is the voice someone's voice?" For speaker identification, will try to find an answer: "the voice is whose voice?" It can be thought that verification is a special case of open-set identification. In this work, deep learning model using a convolution neural network (CNN) for speaker identification is proposed. The voice input to the method is no constrained on the words the speaker speaks. That means it is in a form of text-independent of which more difficult than text-dependent system. By the method, each 2 seconds of the speaker voice is transform to a spectrogram image and input to the generated CNN model training from scratch. The proposed CNN based method is compared to the classic Mel-frequency cepstral coefficients (MFCCs) based featured extraction method classified by support vector machine (SVM). Where, up to date, MFCC is the most popular feature extracted method for audio and speech signal. Our proposed method that the spectrogram image is used as an input is also compared to a case when image of raw signal wave is employed to the CNN model. Experiments are conducted on the speech from five speakers speak in Thai language of which voices are extracted from YouTube. It reveals the proposed CNN based method trains on spectrogram image of voice is the best compared to the other two methods. The average classification results of the testing set by the proposed method is 95.83%. For MFCC based method is 91.26% and for CNN model trained on image of raw signal wave is only 49.77%. The proposed method is very efficient when only short utterance of voice is used as an input.Index Terms-Convolution neural network (CNN), deep learning, speaker recognition, speaker identification, text-independent.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Text-Independent Speaker Identification Using Deep Learning Model of Convolution Neural Network

Bunrit¹,

Inkian²,

Kerdprasop³

et al. 2019

IJMLC

View full text Add to dashboard Cite

show abstract

“…In the era of “big data,” transformation of large quantities of data into valuable knowledge has become increasingly important in various domains, such as the image recognition, speech recognition, and the EEG signals are also included in it. With the current exponential growth of the amount of data available, the large number of different formats, and the increasing computational power, and taking into account the expectations generated by Artificial Intelligence, as a new powerful tool to the service of humans and companies, many studies began focusing on EEG's research.…”

Section: Introductionmentioning

confidence: 99%

Deep learning for EEG data analytics: A survey

Lee

Jung

et al. 2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary In this work, we conducted a literature review about deep learning (DNN, RNN, CNN, and so on) for analyzing EEG data for decoding the activity of human's brain and diagnosing disease and explained details about various architectures for understanding the details of CNN and RNN. It has analyzed a word, which presented a model based on CNN and LSTM methods, and how these methods can be used to both optimize and set up the hyper parameters of deep learning architecture. Later, it is studied how semi‐supervised learning on EEG data analytics can be applied. We review some studies about different methods of semi‐supervised learning on EEG data analytics and discussing the importance of semi‐supervised learning for analyzing EEG data. In this paper, we also discuss the most common applications for human EEG research and review some papers about the application of EEG data analytics such as Neuromarketing, human factors, social interaction, and BCI. Finally, some future trends of development and research in this area, according to the theoretical background on deep learning, are given.

show abstract

“…Leu, G.‐L. Lin, and H. Susanto was presented a new speaker identification system named mel frequency cepstral coefficients (MFCC), which allow to perform speaker identification for access control. Speaker identification is performed in in frequency domain, and the system uses human auditory filtering model to adjust the energy levels of different frequencies of voice quantified features.…”

mentioning

confidence: 99%

Bio‐inspired and cognitive approaches in cryptography and security applications

Ogiela

2017

Concurrency and Computation

View full text Add to dashboard Cite

The modern solutions in Internet technologies like IoT, Cloud, and Pervasive computing, as well as new computation approaches are due to the rapid development of the critical infrastructure and also different methods, providing the secure communication between remoted peers. Recent progress in ubiquitous computing is made possible, thanks to the application of the cutting edge achievements in soft computing, cognitive infor- These subjects, as well as a number of others, like the innovative and secure applications, as well as the ways of using biologically inspired and cognitive procedures, computational models and secure communication protocols, smart services, or pervasive computing will form the subject of this Special Issue on "Bio-inspired and cognitive approaches in cryptography and security applications" in the Concurrency and Computation: Prac-

show abstract

An MFCC‐based text‐independent speaker identification system for access control

Cited by 37 publications

References 25 publications

Text-Independent Speaker Identification Using Deep Learning Model of Convolution Neural Network

Text-Independent Speaker Identification Using Deep Learning Model of Convolution Neural Network

Deep learning for EEG data analytics: A survey

Bio‐inspired and cognitive approaches in cryptography and security applications

Contact Info

Product

Resources

About