Speaker Identification System Research Articles

Exploring the Impact of Mismatch Conditions, Noisy Backgrounds, and Speaker Health on Convolutional Autoencoder-Based Speaker Recognition System with Limited Dataset

This paper presents a novel approach to enhance the success rate and accuracy of speaker recognition and identification systems. The methodology involves employing data augmentation techniques to enrich a small dataset with audio recordings from five speakers, covering both male and female voices. Python programming language is utilized for data processing, and a convolutional autoencoder is chosen as the model. Spectrograms are used to convert speech signals into images, serving as input for training the autoencoder. The developed speaker recognition system is compared against traditional systems relying on the MFCC feature extraction technique. In addition to addressing the challenges of a small dataset, the paper explores the impact of a "mismatch condition" by using different time durations of the audio signal during both training and testing phases. Through experiments involving various activation and loss functions, the optimal pair for the small dataset is identified, resulting in a high success rate of 92.4% in matched conditions. Traditionally, Mel-Frequency Cepstral Coefficients (MFCC) have been widely used for this purpose. However, the COVID-19 pandemic has drawn attention to the virus's impact on the human body, particularly on areas relevant to speech, such as the chest, throat, vocal cords, and related regions. COVID-19 symptoms, such as coughing, breathing difficulties, and throat swelling, raise questions about the influence of the virus on MFCC, pitch, jitter, and shimmer features. Therefore, this research aims to investigate and understand the potential effects of COVID-19 on these crucial features, contributing valuable insights to the development of robust speaker recognition systems.

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.

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

<p><span>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</span><span>.</span></p>

Enhancing speaker identification through reverberation modeling and cancelable techniques using ANNs.

This paper introduces a method aiming at enhancing the efficacy of speaker identification systems within challenging acoustic environments characterized by noise and reverberation. The methodology encompasses the utilization of diverse feature extraction techniques, including Mel-Frequency Cepstral Coefficients (MFCCs) and discrete transforms, such as Discrete Cosine Transform (DCT), Discrete Sine Transform (DST), and Discrete Wavelet Transform (DWT). Additionally, an Artificial Neural Network (ANN) serves as the classifier for this method. Reverberation is modeled using varying-length comb filters, and its impact on pitch frequency estimation is explored via the Auto Correlation Function (ACF). This paper also contributes to the field of cancelable speaker identification in both open and reverberation environments. The proposed method depends on comb filtering at the feature level, deliberately distorting MFCCs. This distortion, incorporated within a cancelable framework, serves to obscure speaker identities, rendering the system resilient to potential intruders. Three systems are presented in this work; a reverberation-affected speaker identification system, a system depending on cancelable features through comb filtering, and a novel cancelable speaker identification system within reverbration environments. The findings revealed that, in both scenarios with and without reverberation effects, the DWT-based features exhibited superior performance within the speaker identification system. Conversely, within the cancelable speaker identification system, the DCT-based features represent the top-performing choice.

Text-independent speaker identification system using discrete wavelet transform with linear prediction coding

AbstractOne of the key problems of the modern day is the presentation of an identity verification system that can perform sufficient accuracy in identity verification, is resilient to assaults and noises, and can be recorded in the simplest possible method. In this study, a new speaker feature extraction which based on discrete wavelet transform (DWT) and linear prediction coding (LPC) algorithm (WLPCA) are investigated. This paper's primary objective is to evidence the performance of the new method for speaker identification by a Gaussian mixture model (GMM). The proposed method improves the recognition rate over the Mel-frequency cepstral coefficient (MFCC). Experimental evaluation of the process performance is performed on two speech databases; our recorded database and the publicly available TIMIT database. We show that the speech features derived by the newly proposed method are more suitable for GMM (91.53%), in terms of the time-consumed, by requiring less Gaussian mixtures than MFCC (85.77%). For testing the presented method in a noisy environment, Additive white Gaussian noise (AWGN) was added to the TIMIT database, where a slight improvement in the performance of the presented method (60.02%) over the MFCC (59.89%) was observed.

Quran reciter identification using NASNetLarge

AbstractSpeaker identification has significant advantages for the field of human–computer interaction. Recently, many scholars have made contributions in this field and successfully created deep learning models for automatic speaker identification systems. However, most of the speech signal processing work is limited to English-only applications, despite numerous challenges with Arabic speech, particularly with the recitation of the Holy Quran, which is the Islamic holy book. In the light of these considerations, this study proposes a model for identifying the reciter of the Holy Quran using a dataset of 11,000 audio samples extracted from 20 Quran reciters. To enable feeding the audio samples' visual representation to the pre-trained models, the audio samples are converted from their original audio representation to visual representation using the Mel-Frequency Cepstrum Coefficients. Six pre-trained deep learning models are evaluated separately in the proposed model. The results from the test dataset reveal that the NASNetLarge model achieved the highest accuracy rate of 98.50% among the pre-trained models used in this study.

Analysis of Machine Learning Classifiers for Speaker Identification: A Study on SVM, Random Forest, KNN, and Decision Tree

This study investigates the performance of machine learning classifiers in the domain of speaker identification, a pivotal component of modern digital security systems. With the burgeoning integration of voice-activated interfaces in technology, the demand for accurate and reliable speaker identification is paramount. This research provides a comprehensive comparison of four widely used classifiers: Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), and Decision Tree (DT). Utilizing the LibriSpeech dataset, known for its diversity of speakers and recording conditions, we extracted Mel-frequency cepstral coefficients (MFCCs) to serve as features for training and evaluating the classifiers. Each model's performance was assessed based on precision, recall, F1-score, and accuracy. The results revealed that RF outperformed all other classifiers, achieving near-perfect metrics, indicative of its robustness and generalizability for speaker identification tasks. KNN also demonstrated high performance, suggesting its suitability for applications where rapid execution and interpretability are critical. Conversely, SVM and DT, while yielding moderate and lower performances respectively, highlighted the necessity for further optimization. These findings underscore the effectiveness of ensemble and distance-based classifiers in handling complex patterns for speaker differentiation. The study not only guides the selection of appropriate classifiers for speaker identification but also sets the stage for future research, which could explore hybrid models and the impact of dataset variability on performance. The insights from this analysis contribute significantly to the field, providing a benchmark for developing advanced speaker identification systems

Optimizing Speaker Identification through SincsquareNet and SincNet Fusion with Attention Mechanism

Advancements in machine learning and deep learning benefit access control systems, forensics, and biometrics particularly in speaker identification systems. The SincNet architecture is a distinct convolutional neural network (CNN) designed for speaker identification. It operates by taking one-dimensional raw speech and directing it through its initial convolutional layer, consisting of Sinc filters. In this work, we present a SincsquareNet, a CNN that efficiently learns customized triangular band-pass filters using trainable Sinc-squared functions. Also, we propose the fusion of SincsqaureNet with SincNet for robust speaker identification. Further, a self-attention mechanism is employed to obtain discriminating features. The Librispeech dataset is used to validate the proposed framework. This approach makes use of the best of both filters, helps the network learn more robust features, and converges faster. The findings of the experiments show that, when compared to SincsquareNet, speaker identification accuracy was relatively improved by 8%, while validation loss was reduced by 7%.

An efficient Automatic Speaker Identification System based Pitch Frequency Estimation in Degraded Environmental Conditions

An efficient Automatic Speaker Identification System based Pitch Frequency Estimation in Degraded Environmental Conditions

A text independent speaker identification system using ANN, RNN, and CNN classification technique

A text independent speaker identification system using ANN, RNN, and CNN classification technique

Speaker Identification in Multiple Languages: Regional, Indonesian, and English with Short Utterance

One of the authentication models that are currently often used is based on biometrics, such as eye retina, fingerprint, and speech recognition. Moreover, textindependent speaker identification is one of the domains of speech recognition that has been widely studied. Short speech duration in the speaker identification process is one of the challenges in the field of speaker recognition. Accuracy is a great issue when speech duration shorter, besides identification system has to be general enough to process various languages with different dialects which have their own characteristic based on tribe and region. Therefore, the author of this study introduces the speaker identification system in multi languages that comprise of regional, Indonesian, and English with short utterance. Researchers used MFCC technique to extract voice features and CNN as the classification model. There are two kinds of dataset used, open dataset for regional and English language, and own dataset for Indonesian. Own dataset used is a voice recording of 18 persons of different gender who each read the text in several paragraphs of sentences in Indonesian. Whereas public dataset of regional language used consisted of 80 speakers, 41 Sundanese and 39 Javanese. As for English dataset, 126 male speakers and 125 female speakers were taken from LibriSpeech. Tests are carried out separately with variety of language and speech duration, about 3 seconds in English and regional languages, 1 and 3 seconds in Indonesian. The result, best accuracy obtained by each dataset is 95% (regional dataset), 94% (English dataset), and 98% (private dataset).

Evaluation of Machine Learning Algorithms using Combined Feature Extraction Techniques for Speaker Identification

The aim of this study is to evaluate and compare machine learning algorithms when various feature extraction techniques are employed together and determine the optimal feature combinations for the models studied. The TIMIT online database was used where 5 male and 5 female non-native English speakers from five American locations were selected. Each speaker had ten 3-second utterances, totaling 500. Mel frequency cepstral coefficients (MFCC), linear predictive cepstral coefficients (LPCC), gammatone frequency cepstral coefficients (GFCC), discrete wavelet transforms (DWT) and pitch features were extracted using MATLAB and concatenated. The concatenated features were used to train and evaluate three classifier models—Random Forest (RF), Linear Discriminant Analysis (LDA), and Logistic Regression (LR)—using Python software. The results obtained showed that as the number of features combinations increased, the models’ performances improved as well. This improved performance was observed when all the cepstral features were part of the combinations. This implies that cepstral features are more robust and improve speaker identification systems. The best average score of accurate predictions of ≈ 76% for the LR model was obtained for the MGL (39 features) features combination and dropped to 70% for the highest number of feature combinations MGDLP (53 features). This indicates that more training data improves system performance, however, too much data does not translate to even better performance because the system will eventually achieve its peak performance. This information is useful for applications where limited data can present a problem.

Analysis and Investigation of Speaker Identification Problems Using Deep Learning Networks and the YOHO English Speech Dataset

The rapid momentum of deep neural networks (DNNs) in recent years has yielded state-of-the-art performance in various machine-learning tasks using speaker identification systems. Speaker identification is based on the speech signals and the features that can be extracted from them. In this article, we proposed a speaker identification system using the developed DNNs models. The system is based on the acoustic and prosodic features of the speech signal, such as pitch frequency (vocal cords vibration rate), energy (loudness of speech), their derivations, and any additional acoustic and prosodic features. Additionally, the article investigates the existing recurrent neural networks (RNNs) models and adapts them to design a speaker identification system using the public YOHO LDC dataset. The average accuracy of the system was 91.93% in the best experiment for speaker identification. Furthermore, this paper helps uncover reasons for analyzing speakers and tokens yielding major errors to increase the system’s robustness regarding feature selection and system tune-up.

Face mask effects on speaker verification performance in the presence of noise.

Due to its spread via physical contact and the regulations on wearing face masks, COVID-19 has resulted in tough challenges for speaker recognition. Masks may aid in preventing COVID-19 transmission, although the implications of the mask on system performance in a clean environment and with varying levels of background noise are unclear. The face mask has an impact on speech output. The task of comprehending speech while wearing a face mask is made more difficult by the mask's frequency response and radiation qualities, which is vary depending on the material and design of the mask. In this study, we recorded speech while wearing a face mask to see how different masks affected a state-of-the-art text-independent speaker verification system using an i-vector speaker identification system. This research investigates the influence of facial coverings on speaker verification. To address this, we investigated the effect of fabric masks on speaker identification in a cafeteria setting. These results present preliminary speaker recognition rates as well as mask verification trials. The result shows that masks had little to no effect in low background noise, with an EER of 2.4-2.5% in 20dB SNR for both masks compared to no mask at the same level. In noisy conditions, accuracy was 12.7-13.0% lowers than without a mask with a 5dB SNR, indicating that while different masks perform similarly in low background noise levels, they become more noticeable in high noise levels.

Enhanced Multiple Speakers’ Separation and Identification for VOIP Applications Using Deep Learning

Institutions have been adopting work/study-from-home programs since the pandemic began. They primarily utilise Voice over Internet Protocol (VoIP) software to perform online meetings. This research introduces a new method to enhance VoIP calls experience using deep learning. In this paper, integration between two existing techniques, Speaker Separation and Speaker Identification (SSI), is performed using deep learning methods with effective results as introduced by state-of-the-art research. This integration is applied to VoIP system application. The voice signal is introduced to the speaker separation and identification system to be separated; then, the “main speaker voice” is identified and verified rather than any other human or non-human voices around the main speaker. Then, only this main speaker voice is sent over IP to continue the call process. Currently, the online call system depends on noise cancellation and call quality enhancement. However, this does not address multiple human voices over the call. Filters used in the call process only remove the noise and the interference (de-noising speech) from the speech signal. The presented system is tested with up to four mixed human voices. This system separates only the main speaker voice and processes it prior to the transmission over VoIP call. This paper illustrates the algorithm technologies integration using DNN, and voice signal processing advantages and challenges, in addition to the importance of computing power for real-time applications.

Enhancement in Speaker Identification through Feature Fusion using Advanced Dilated Convolution Neural Network

There are various challenges in identifying the speakers accurately. The Extraction of discriminative features is a vital task for accurate identification in the speaker identification task. Nowadays, speaker identification is widely investigated using deep learning. The complex and noisy speech data affects the performance of Mel Frequency Cepstral Coefficients (MFCC); hence, MFCC fails to represent the speaker characteristics accurately. In this proposed work, a novel text-independent speaker identification system is developed to enhance the performance by fusion of Log-MelSpectrum and excitation features. The excitation information is obtained due to the vibration of vocal folds, and it is represented using Linear Prediction (LP) residual. The various types of features extracted from the excitation are residual phase, sharpness, Energy of Excitation (EoE), and Strength of Excitation (SoE). The extracted features were processed with the dilated convolution neural network (dilated CNN) to fulfill the identification task. The extensive evaluation showed that the fusion of excitation features gives better results than the existing methods. The accuracy reaches 94.12% for 11 complex classes and 91.34% for 80 speakers, and Equal Error Rate (EER) is reduced to 1.16% for the proposed model. The proposed model is tested with the Librispeech corpus using Matlab 2021b tool, outperforming the existing baseline models. The proposed model achieves an accuracy improvement of 1.34% compared to the baseline system.

Closed-set automatic speaker identification using multi-scale recurrent networks in non-native children.

Children may benefit from automatic speaker identification in a variety of applications, including child security, safety, and education. The key focus of this study is to develop a closed-set child speaker identification system for non-native speakers of English in both text-dependent and text-independent speech tasks in order to track how the speaker's fluency affects the system. The multi-scale wavelet scattering transform is used to compensate for concerns like the loss of high-frequency information caused by the most widely used mel frequency cepstral coefficients feature extractor. The proposed large-scale speaker identification system succeeds well by employing wavelet scattered Bi-LSTM. While this procedure is used to identify non-native children in multiple classes, average values of accuracy, precision, recall, and F-measure are being used to assess the performance of the model in text-independent and text-dependent tasks, which outperforms the existing models.

Development of Supervised Speaker Diarization System Based on the PyAnnote Audio Processing Library.

Diarization is an important task when work with audiodata is executed, as it provides a solution to the problem related to the need of dividing one analyzed call recording into several speech recordings, each of which belongs to one speaker. Diarization systems segment audio recordings by defining the time boundaries of utterances, and typically use unsupervised methods to group utterances belonging to individual speakers, but do not answer the question "who is speaking?" On the other hand, there are biometric systems that identify individuals on the basis of their voices, but such systems are designed with the prerequisite that only one speaker is present in the analyzed audio recording. However, some applications involve the need to identify multiple speakers that interact freely in an audio recording. This paper proposes two architectures of speaker identification systems based on a combination of diarization and identification methods, which operate on the basis of segment-level or group-level classification. The open-source PyAnnote framework was used to develop the system. The performance of the speaker identification system was verified through the application of the AMI Corpus open-source audio database, which contains 100 h of annotated and transcribed audio and video data. The research method consisted of four experiments to select the best-performing supervised diarization algorithms on the basis of PyAnnote. The first experiment was designed to investigate how the selection of the distance function between vector embedding affects the reliability of identification of a speaker's utterance in a segment-level classification architecture. The second experiment examines the architecture of cluster-centroid (group-level) classification, i.e., the selection of the best clustering and classification methods. The third experiment investigates the impact of different segmentation algorithms on the accuracy of identifying speaker utterances, and the fourth examines embedding window sizes. Experimental results demonstrated that the group-level approach offered better identification results were compared to the segment-level approach, and the latter had the advantage of real-time processing.

인공지능 학습모델과 음향데이터를 이용한 군사장비 식별

Acoustic data is widely used for the development of voice recognition based services, speaker identification system, or environmental sound classification. However, in the defense sector, research on the use of acoustic data and AI learning models has not yet been actively conducted. In addition, collection methods or quality standards that must be considered in order to use acoustic data as training data have not been clearly established. Therefore, this paper attempts to classify six weapons for the first time using four AI learning models and previously collected acoustic data to derive considerations in the process of collecting acoustic data. The learning data used in the experiment is acoustic data related to Army equipment collected through a government-supported project in the second half of 2021. Experimental results show that the classification performance of CNN and LightGBM models is generally high and the best performance is achieved when the data has a medium length. By uniformly re-configuring the number of data per class using SMOTE, the performance can be further improved. Based on these experimental results, we also propose what should be considered when constructing AI training data for classification of military equipment based on acoustic data.

Speaker identification and localization using shuffled MFCC features and deep learning

The use of machine learning in automatic speaker identification and localization systems has recently seen significant advances. However, this progress comes at the cost of using complex models, computations, and increasing the number of microphone arrays and training data. Therefore, in this work, we propose a new end-to-end identification and localization model based on a simple fully connected deep neural network (FC-DNN) and just two input microphones. This model can jointly or separately localize and identify an active speaker with high accuracy in single and multi-speaker scenarios by exploiting a new data augmentation approach. In this regard, we propose using a novel Mel Frequency Cepstral Coefficients (MFCC) based feature called Shuffled MFCC (SHMFCC) and its variant Difference Shuffled MFCC (DSHMFCC). In order to test our approach, we analyzed the performance of the identification and localization proposed model on the new features at different noise and reverberation conditions for single and multi-speaker scenarios. The results show that our approach achieves high accuracy in these scenarios, outperforms the baseline and conventional methods, and achieves robustness even with small-sized training data.