Speaker Identification Techniques Research Articles

DEEP LEARNING IN SPEAKER IDENTIFICATION: MODERN METHODS AND DEVELOPMENT PROSPECTS

The article contains a review of the research on the use of deep learning in speaker identification. It examines the problems of voice identification, highlighting the relevance and the need for effective methods in this area. The evolution of speaker identification techniques from simple pattern matching to complex neural architectures is traced to understand the technological advancements in this field. Modern methods for speaker identification and the prospects for the development of such systems are considered. The two aims set by the authors are: to make comparative analysis of deep learning with traditional methods and to review the current state of technology. First they highlight the key differences and advantages of deep learning compared to traditional approaches to speaker identification, describe the challenges in deep learning methods, such as the necessity for large datasets and computational resources, and analyse how these issues are addressed by the research community. Then the authors provide a comprehensive overview of the current deep learning methods used for speaker identification, including the latest breakthroughs and innovations in neural network architectures, training techniques, and feature extraction methods. The potential of unsupervised and semi-supervised learning paradigms to further enhance speaker identification systems is explored, offering insights into the future research in this field. Key words: deep learning, speaker identification, neural networks, recurrent layers, convolutional layers, voice recognition technologies.

Comparing Machine Learning Models to Determine the Effect of Speech Duration on Speaker Identification within Kazakh Speech Corpus

This paper conducts comparative analysis of speaker identification techniques, namely Gaussian Mixture Models (GMM), Bidirectional Long Short-Term Memory (BiLSTM) neural networks, and Recurrent Neural Networks (RNN), applied to the Kazakh Speech Corpus. The study's central objective is to explore the influence of speech duration on the efficacy of speaker identification. Our results indicate that all models exhibit enhanced accuracy with increased speech duration. Furthermore, the incorporation of delta and fundamental frequency (F0) as supplementary features bolsters the performance of these models. This research contributes to the understanding of how speech duration and additional features can optimize speaker identification techniques, providing valuable insights for future developments in the field.

Text dependent speaker identification system based on deep learning

Speaker identification techniques are one of those most advanced modern technologies and there are many different systems had been developed, from methods that used to extract characteristics and classification. The applications of Speech identification are quite difficult and requires modern technologies with a large number of audio samples and resources. In this research, the system of speaker identification had been designed based on a text (the word or sentences are pre-defined) which give the system the capability to identify the speaker in the least time, number of training samples and resources. The system consists four main parts, the first one is to create audio databases. In the study, two audio databases were relied upon, the first being a database (QS- Dataset) and the second database (audioMNIST_meta). The databases were processed and configured in a way that was explained in the body of the research later. The second part of the research is to extract the characteristics through the pitch coefficients algorithm, while the third part is the use of the neural network as a classifier. And the last part of the research is to verify the work and results of the system. The test results showed the ability of the MNN network to deal with the smallest number of data, as it achieved a percentage of 100%. As for large data, it ranged from 80% to 81%. Unlike CNN network, the results were not good for the few data, from 60% to 76%, and with large data it was The results are excellent, from 91% to 96%.

Efficient Implementation of Radon Transform and Encryption Techniques for Cancelable Speaker Identification

This paper introduces three cancelable speaker identification techniques based on the spectrogram estimation of speech signals subjected to either chaotic encryption process, or RSA algorithm in addition to Radon transform to produce cancelable templates instead of the original speech signals. The resulting transformed versions of the voice biometrics are stored in the server instead of the original biometrics. Therefore, the users' privacy can be protected well. It is evident from the obtained results that the proposed techniques are secure, reliable and practical. They have good encryption and ability to generate cancelable templates. These characteristics lead to good performance. The proposed cancelable speaker identification techniques are evaluated under the influence of Additive White Gaussian Noise (AWGN) with different strengths. This makes them more accurate in identifying the users and also more resistant to attack attempts. In addition, security is enhanced through maintaining the confidentiality of the processed data. In the experimental results, evaluation metrics such as Equal Error Rate (EER), False Rejection Rate (FRR), and False Acceptance Rate (FAR) are used to assess the performance of the proposed techniques. In addition, the genuine, impostor distributions, Receiver Operating Characteristic (ROC) curve and area under the ROC curve for the proposed techniques are estimated for better evaluation and comparison.

An Encapsulation of Vital Non-Linear Frequency Features for Various Speech Applications

Mel Frequency Cepstral Coefficients (MFCCs) and Perceptual linear prediction coefficients (PLPCs) are widely casted nonlinear vocal parameters in majority of the speaker identification, speaker and speech recognition techniques as well in the field of emotion recognition. Post 1980s, significant exertions are put forth on for the progress of these features. Considerations like the usage of appropriate frequency estimation approaches, proposal of appropriate filter banks, and selection of preferred features perform a vital part for the strength of models employing these features. This article projects an overview of MFCC and PLPC features for different speech applications. The insights such as performance metrics of accuracy, background environment, type of data, and size of features are inspected and concise with the corresponding key references. Adding more to this, the advantages and shortcomings of these features have been discussed. This background work will hopefully contribute to floating a heading step in the direction of the enhancement of MFCC and PLPC with respect to novelty, raised levels of accuracy, and lesser complexity.

Speaker identification using convolutional-long short-term memory neural networks

Speaker identification (SI) techniques has been used in numerous commercial products over the last decades. In SI, the main purpose is to match a voice sample from an unknown speaker to one of the labeled speaker models. To be able accomplish this task, there are two operational phases, training (can be also termed as enrollment) and testing. In both phases, feature extraction and feature matching are the two key steps. In this work, we have extracted features with Mel-Frequency Cepstrum Coefficients (MFCC) because MFCC has accurate representation of the vocal tract, and a Spectral-Flux based Voice Activity Detector (VAD) is implemented to extract features from the speech segments. In feature matching task, we build a Convolutional Long short-term memory (LSTM) Neural Network for the speaker models. We examine main performance of the system in terms of identification rate and compare the proposed method with other SI methods under several noisy conditions at different signal to noise ratio (SNR) levels.Speaker identification (SI) techniques has been used in numerous commercial products over the last decades. In SI, the main purpose is to match a voice sample from an unknown speaker to one of the labeled speaker models. To be able accomplish this task, there are two operational phases, training (can be also termed as enrollment) and testing. In both phases, feature extraction and feature matching are the two key steps. In this work, we have extracted features with Mel-Frequency Cepstrum Coefficients (MFCC) because MFCC has accurate representation of the vocal tract, and a Spectral-Flux based Voice Activity Detector (VAD) is implemented to extract features from the speech segments. In feature matching task, we build a Convolutional Long short-term memory (LSTM) Neural Network for the speaker models. We examine main performance of the system in terms of identification rate and compare the proposed method with other SI methods under several noisy conditions at different signal to noise ratio (SNR) levels.

Probabilistic Self-Organizing Maps for Text-Independent Speaker Identification

The present paper introduces a novel speaker modeling technique for text-independent speaker identification using probabilistic self-organizing maps (PbSOMs). The basic motivation behind the introduced technique was to combine the self-organizing quality of the self-organizing maps and generative power of Gaussian mixture models. Experimental results show that the introduced modeling technique using probabilistic self-organizing maps significantly outperforms the traditional technique using the classical GMMs and the EM algorithm or its deterministic variant. More precisely, a relative accuracy improvement of roughly 39% has been gained, as well as, a much less sensitivity to the model-parameters initialization has been exhibited by using the introduced speaker modeling technique using probabilistic self-organizing maps.

Towards the identification of Idiopathic Parkinson's Disease from the speech. New articulatory kinetic biomarkers.

Although a large amount of acoustic indicators have already been proposed in the literature to evaluate the hypokinetic dysarthria of people with Parkinson’s Disease, the goal of this work is to identify and interpret new reliable and complementary articulatory biomarkers that could be applied to predict/evaluate Parkinson’s Disease from a diadochokinetic test, contributing to the possibility of a further multidimensional analysis of the speech of parkinsonian patients. The new biomarkers proposed are based on the kinetic behaviour of the envelope trace, which is directly linked with the articulatory dysfunctions introduced by the disease since the early stages. The interest of these new articulatory indicators stands on their easiness of identification and interpretation, and their potential to be translated into computer based automatic methods to screen the disease from the speech. Throughout this paper, the accuracy provided by these acoustic kinetic biomarkers is compared with the one obtained with a baseline system based on speaker identification techniques. Results show accuracies around 85% that are in line with those obtained with the complex state of the art speaker recognition techniques, but with an easier physical interpretation, which open the possibility to be transferred to a clinical setting.

BPN Based Likelihood Ratio Score Fusion for Audio-Visual Speaker Identification in Response to Noise

This paper deals with a new and improved approach of Back-propagation learning neural network based likelihood ratio score fusion technique for audio-visual speaker Identification in various noisy environments. Different signal preprocessing and noise removing techniques have been used to process the speech utterance and LPC, LPCC, RCC, MFCC, ΔMFCC and ΔΔMFCC methods have been applied to extract the features from the audio signal. Active Shape Model has been used to extract the appearance and shape based facial features. To enhance the performance of the proposed system, appearance and shape based facial features are concatenated and Principal Component Analysis method has been used to reduce the dimension of the facial feature vector. The audio and visual feature vectors are then fed to Hidden Markov Model separately to find out the log-likelihood of each modality. The reliability of each modality has been calculated using reliability measurement method. Finally, these integrated likelihood ratios are fed to Back-propagation learning neural network algorithm to discover the final speaker identification result. For measuring the performance of the proposed system, three different databases, that is, NOIZEUS speech database, ORL face database and VALID audio-visual multimodal database have been used for audio-only, visual-only, and audio-visual speaker identification. To identify the accuracy of the proposed system with existing techniques under various noisy environment, different types of artificial noise have been added at various rates with audio and visual signal and performance being compared with different variations of audio and visual features.

Investigation of Decision Tree Induction, Probabilistic Technique and SVM For Speaker Identification

Speaker recognition and speech recognition are both related. As against determining what was said, speaker recognition enables the automatic recognition of who is speaking based on the speaker’s voice’s unique characteristics. This paper presents a simple approach to text dependent speaker identification and is based on the Symlet wavelets for feature extraction. The extracted features are then classified using data mining algorithms. In this study, J48, Naive Bayes and SVM are used for classifying the features.

Convolutive ICA-Based Forensic Speaker Identification Using Mel Frequency Cepstral Coefficients and Gaussian Mixture Models

Automatic speaker identification techniques are widely used nowadays in forensic applications, but its accuracy harshly drops when the voice of the speaker of interest is immersed in a recording containing more than one voice, common situation of investigations where the targets voice are obtained through ambient recordings. In forensic applications where microphones are hidden, such interferent sound sources in recordings are common and they degrade severely the performance of speaker identification techniques. In this paper, we propose a method to mitigate this problem by spatially separating the voice of each speaker using a Blind Source Separation technique called Convolutive Independent Component Analysis, and then applying the separated speech signals to a speaker identification system based on Mel Frequency Cepstral Coefficients and Gaussian Mixture Models. For identifying more than one speaker, the proposed system has a better accuracy than the state-of-the-art solutions.

커널 주성분 분석의 앙상블을 이용한 다양한 환경에서의 화자 식별

In this paper, we propose a new approach to speaker identification technique which uses an ensemble of multiple classifiers (speaker identifiers). KPCA (kernel principal component analysis) enhances features for each classifier. To reduce the processing time and memory requirements, we select limited number of samples randomly which are used as estimation set for each KPCA basis. The experimental result shows that the proposed approach gives a higher identification accuracy than GKPCA (greedy kernel principal component analysis).

Colored Noise Based Multicondition Training Technique for Robust Speaker Identification

This letter proposes a colored noise based multicondition training technique for robust speaker identification in unknown noisy environments. The colored noise samples generation is based on filtering a white Gaussian sequence that leads to a power spectral density (PSD) proportional to 1/ <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">f</i> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">β</sup> , where β ∈ [0, 2]. Gaussian mixture models (GMM) are applied to obtain the speaker models using the noisy speech signals with a single signal-to-noise ratio (SNR). The colored noise based multicondition training is evaluated for the speaker identification task considering the test utterances corrupted with real acoustic noises and different values of SNR. The results show that the proposed technique outperforms the white noise based multicondition and the clean-speech training approaches.

A Novel Feature Extraction Technique for Speaker Identification

paper presents a novel feature extraction approach for speaker identification when the speech is corrupted by additive noise. The environmental mismatch between training and testing data degrades the performance of speaker identification system. The performance degradation is primarily due to presence of background noise when try to match a given speaker to the set of known speakers in a database. Mel frequency cepstral coefficients (MFCCs) are perhaps the most widely used front ends in the state of the art speaker identification systems. One of the major issues with MFCCs is that they are very sensitive to additive noise. To overcome this bottleneck, a temporal filtering procedure on the autocorrelation sequence is proposed to minimize the effect of additive noise. The proposed feature is called Relative Autocorrelation Mel Frequency Cepstral Coefficients (A-MFCC) which is derived based on filtering the temporal trajectories of short time one sided autocorrelation sequence. This filtering process minimizes the effect of additive noise. No prior knowledge of noise characteristics is required. The additive noise can be a colored noise. For speaker identification, Hindi database was constructed from the speech samples of each known speaker. Feature vectors (MFCCs and A-MFCCs) were extracted from the samples by short-term spectral analysis, and processed further by vector quantization for locating the clusters in the feature space. Experimental results indicated that A-MFCCs significantly improved the performance of speaker identification system in noisy environment.

Speaker identification based on the frame linear predictive coding spectrum technique

In this paper, a frame linear predictive coding spectrum (FLPCS) technique for speaker identification is presented. Traditionally, linear predictive coding (LPC) was applied in many speech recognition applications, nevertheless, the modification of LPC termed FLPCS is proposed in this study for speaker identification. The analysis procedure consists of feature extraction and voice classification. In the stage of feature extraction, the representative characteristics were extracted using the FLPCS technique. Through the approach, the size of the feature vector of a speaker can be reduced within an acceptable recognition rate. In the stage of classification, general regression neural network (GRNN) and Gaussian mixture model (GMM) were applied because of their rapid response and simplicity in implementation. In the experimental investigation, performances of different order FLPCS coefficients which were induced from the LPC spectrum were compared with one another. Further, the capability analysis on GRNN and GMM was also described. The experimental results showed GMM can achieve a better recognition rate with feature extraction using the FLPCS method. It is also suggested the GMM can complete training and identification in a very short time.

Constructing and application of multimedia TV-news archives

This paper addresses an integrated information mining techniques for broadcasting TV-news. This utilizes technique from the fields of acoustic, image, and video analysis, for information on news story title, newsman and scene identification. The goal is to construct a compact yet meaningful abstraction of broadcast TV-news, allowing users to browse through large amounts of data in a non-linear fashion with flexibility and efficiency. By adding acoustic analysis, a news program can be partitioned into news and commercial clips, with 90% accuracy on a data set of 400h TV-news recorded off the air from July 2005 to August 2006. By applying speaker identification and/or image detection techniques, each news stories can be segmented with a better accuracy of 95.92%. On-screen captions or subtitles are recognized by OCR techniques to produce the text title of each news stories. The extracted title words can be used to link or to navigate more related news contents on the WWW. In cooperation with facial and scene analysis and recognition techniques, OCR results can provide users with multimodal query on specific news stories. Some experimental results are presented and discussed for the system reliability, performance evaluation and comparison.

Speaker identification based on adaptive discriminative vector quantisation

A novel adaptive discriminative vector quantisation technique for speaker identification (ADVQSI) is introduced. In the training mode of ADVQSI, for each speaker, the speech feature vector space is divided into a number of subspaces. The feature space segmentation is based on the difference between the probability distribution of the speech feature vectors from each speaker and that from all speakers in the speaker identification (SI) group. Then, an optimal discriminative weight, which represents the subspace&apos;s role in SI, is calculated for each subspace of each speaker by employing adaptive techniques. The largest template differences between speakers in the SI group are achieved by using optimal discriminative weights. In the testing mode of ADVQSI, discriminative weighted average vector quantisation (VQ) distortions are used for SI decisions. The performance of ADVQSI is analysed and tested experimentally. The experimental results confirm the performance improvement employing the proposed technique in comparison with existing VQ techniques for SI and recently reported discriminative VQ techniques for SI (DVQSI).

Combination of autocorrelation-based features and projection measure technique for speaker identification

This paper presents a robust approach for speaker identification when the speech signal is corrupted by additive noise and channel distortion. Robust features are derived by assuming that the corrupting noise is stationary and the channel effect is fixed during an utterance. A two-step temporal filtering procedure on the autocorrelation sequence is proposed to minimize the effect of additive and convolutional noises. The first step applies a temporal filtering procedure in autocorrelation domain to remove the additive noise, and the second step is to perform the mean subtraction on the filtered autocorrelation sequence in logarithmic spectrum domain to remove the channel effect. No prior knowledge of noise characteristic is necessary. The additive noise can be a colored noise. Then the proposed robust feature is combined with the projection measure technique to gain further improvement in recognition accuracy. Experimental results show that the proposed method can significantly improve the performance of speaker identification task in noisy environment.

NOVEL DISCRIMINATIVE VECTOR QUANTIZATION APPROACH FOR SPEAKER IDENTIFICATION

A novel Discriminative Vector Quantization method for Speaker Identification (DVQSI) is proposed, and its parameters selection is discussed. In the training mode of this approach, the vector space of speech features is divided into a number of regions. Then, a Vector Quantization (VQ) codebook for each speaker in each region is constructed. For every possible combination of speaker pairs, a discriminative weight is assigned for each region, based on the region's ability to discriminate between the speaker pair. Consequently, the region, which contains a larger distribution difference between the speech feature vector sets of the two speakers in the speaker pair, plays a more important role by assigning it a larger discriminative weight, in identifying the better speaker match from the two speakers. In the testing mode, to identify an unknown speaker, discriminative weighted average VQ distortion pairs are computed for the unknown speaker input waveform. Then, a technique is described that figures out the best match between the unknown waveform and speakers' templates. The proposed DVQSI approach can be considered a generalization of the existing VQ technique for Speaker Identification (VQSI). The method presented here yields better Speaker Identification (SI) accuracy by employing the discriminative weights and space segmentation as design parameters. This is confirmed experimentally. In addition, a computationally efficient implementation of the DVQSI technique is given which uses a tree-structured-like approach to obtain the codebooks.

Fifty years of progress in speaker verification

The modern era in speaker recognition started about 50 years ago at Bell Laboratories with the controversial invention of the voiceprint technique for speaker identification based on expert analysis of speech spectrograms. Early speaker recognition research concentrated on finding acoustic-phonetic features effective in discriminating speakers. The first truly automatic text dependent speaker verification systems were based on time contours or templates of speaker specific acoustic features. An important element of these systems was the ability to time warp sample templates with model templates in order to provide useful comparisons. Most modern text dependent speaker verification systems are based on statistical representations of acoustic features analyzed as a function of time over specified utterances, most particularly the hidden markov model (HMM) representation. Modern text independent systems are based on vector quantization representations and, more recently, on Gaussian mixture model (GMM) representations. An important ingredient of statistically based systems is likelihood ratio decision techniques making use of speaker background models. Some recent research has shown how to extract higher level features based on speaking behavior and combine it with lower level, acoustic features for improved performance. The talk will present these topics in historical order showing the evolution of techniques.