Automatic Speaker Identification Systems Research Articles

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.

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

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.

An Efficient Text-Independent Speaker Identification Using Feature Fusion and Transformer Model

Automatic Speaker Identification (ASI) involves the process of distinguishing an audio stream associated with numerous speakers’ utterances. Some common aspects, such as the framework difference, overlapping of different sound events, and the presence of various sound sources during recording, make the ASI task much more complicated and complex. This research proposes a deep learning model to improve the accuracy of the ASI system and reduce the model training time under limited computation resources. In this research, the performance of the transformer model is investigated. Seven audio features, chromagram, Mel-spectrogram, tonnetz, Mel-Frequency Cepstral Coefficients (MFCCs), delta MFCCs, delta-delta MFCCs and spectral contrast, are extracted from the ELSDSR, CSTR-VCTK, and Ar-DAD, datasets. The evaluation of various experiments demonstrates that the best performance was achieved by the proposed transformer model using seven audio features on all datasets. For ELSDSR, CSTR-VCTK, and Ar-DAD, the highest attained accuracies are 0.99, 0.97, and 0.99, respectively. The experimental results reveal that the proposed technique can achieve the best performance for ASI problems.

Speaker identification based on Radon transform and CNNs in the presence of different types of interference for Robotic Applications

Both automatic speaker identification (ASI) and speech recognition can be utlized now for the control of modern robots. An ASI algorithm can be implemented at a speech interface of the robot to determine the identity of the person allowed to deal with the robot, while speech recognition can be implemented for the interpretation of the order given to the robot. Robustness of the ASI system is a challenging task in the presence of speech degradations such as noise and interference. This study presents a new approach to improve the accuracy of speaker identification in the presence of interference for robot control applications with a convolutional neural network (CNN). First, the speech signal from the speaker is divided into segments, each of which is transformed into a spectrogram, and hence Radon transformation is estimated for this spectrogram. The spectrogram resolves the speech segment into a map of power distribution with both time and frequency. Together, the spectrograms and their Radon transforms are used as inputs to a proposed CNN-based deep learning model. Necessary refinements are undertaken and the resulting optimized “Radon-Deep-Learning Model (RDLM) is compared with a benchmark model. The proposed model consists of six convolutional (CNV) layers followed by six Max. pooling layers, while the benchmark model consists of three CNV layers followed by three Max. pooling layers. Experimental results reveal that the proposed RDLM model achieves a high classification accuracy up to 97.5%, which is more than double the performance reported for some traditional methods that are used for speaker identification.

Un primer acercamiento a la caracterización acústica del habla de niños costarricenses

A medida que la interacción de las personas con las computadoras se hace más extendida, se vuelve más importante el desarrollo de tecnologías para el reconocimiento automático de la voz, la síntesis de voz, así como otras tecnologías relacionadas, considerando a personas de todas las edades, acentos y condiciones. Uno de los grupos humanos que representan desafíos más grandes es el de los niños, debido a las dificultades para grabar suficientes recursos de habla, y la falta de caracterización de su forma de hablar, la cual es particular de cada idioma y acento. Este artículo presenta una primera aproximación para el análisis acústico de niños costarricenses de entre seis y doce años. Estos análisis tienen como objetivo lograr una mejor comprensión de las características del habla producida por este grupo en particular, en términos de propiciar el desarrollo y mejora de los reconocedores automáticos del habla y los sistemas de identificación del hablante.
 Para este propósito realizamos grabaciones de habla de tres niños, las cuales consistieron en palabras aisladas, y comparamos los resultados con tres adultos en términos de los formantes de las vocales. Los formantes proporcionan información sobre el tracto vocal del hablante, y es un parámetro importante para establecer un primer análisis de estas señales. Los resultados muestran diferencias notables entre los niños y los adultos y pueden brindar información útil para futuros estudios en términos de adaptar y desarrollar las tecnologías del habla para esta población.

Nonlinear waveform distortion: Assessment and detection of clipping on speech data and systems

Speech, speaker, and language systems have traditionally relied on carefully collected speech material for training acoustic models. There is an overwhelming abundance of publicly accessible audio material available for training. A major challenge, however, is that such found data is not professionally recorded, and therefore may contain a wide diversity of background noise, nonlinear distortions, or other unknown environmental or technology-based contamination or mismatch. There is a critical need for automatic analysis to screen such unknown data sets before acoustic model development training, or to perform input audio purity screening prior to classification. In this study, we propose a waveform based clipping detection algorithm for naturalistic audio streams and analyze the impact of clipping at different severities on speech quality measures and automatic speaker identification systems. We use the TIMIT and NIST-SRE08 speech corpora as case studies. The results show, as expected, that clipping introduces a nonlinear distortion into clean speech data, which reduces speech quality and performance for speaker recognition. We also investigate what degree of clipping can be present to sustain effective speech system performance. The proposed detection system, which will be released, could potentially contribute to new audio collections for speech and language technology development.

Spectral Subband Centroids for Robust Speaker Identification Using Marginalization-based Missing Feature Theory

Until now, marginalization-based Missing Feature Theory (MFT) for speech classification has been limited to the use of Log Spectral Subband Energies (LSSEs) as features. These features are highly correlated, thus suboptimal for classification with diagonal-covariance Gaussian Mixture Models (GMMs), a common classifier in marginalization-based MFT. In this paper, we propose that Spectral Subband Centroids (SSCs) are more apt for marginalization-based MFT, as they are both decorrelated and spectrally local. Our results show that SSCs as features produce a more robust marginalization-based MFT, diagonal-covariance GMM-based, Automatic Speaker Identification (ASI) system than LSSEs as features, for at all tested SNR values (with Additive White Gaussian Noise (AWGN)). It is also shown that a fully-connected Deep Neural Network (DNN) can accurately estimate the Ideal Binary Mask (IBM) used for MFT.

Helpful Statistics in Recognizing Basic Arabic Phonemes

The recognition of continuous speech is one of the main challenges in the building of automatic speech recognition (ASR) systems, especially when it comes to phonetically complex languages such as Arabic. An ASR system seems to be actually in a blocked alley. Nearly all solutions follow the same general model. The previous research focused on enhancing its performance by incorporating supplementary features. This paper is part of ongoing research efforts aimed at developing a high-performance Arabic speech recognition system for learning and teaching purposes. It investigates a statistical analysis of certain distinctive features of the basic Arabic phonemes which seems helpful in enhancing the performance of a baseline HMM-based ASR system. The statistics are collected using a particular Arabic speech database, which involves ten different male speakers and more than eight hours of speech which covers all Arabic phonemes. In HMM modeling framework, the statistics provided are helpful in establishing the appropriate number of HMM states for each phoneme and they can also be utilized as an initial condition for the EM estimation procedure, which generally, accelerates the estimation process and, thus, improves the performance of the system. The obtained findings are presented and possible applications of automatic speech recognition and speaker identification systems are also suggested.

Speaker Identification System using Gaussian Mixture Model and Support Vector Machines (GMM-SVM) under Noisy Conditions

Background: Automatic Speaker Identification (SID) systems has been a major breakthrough and crucial in many real world applications. Methods: This work addresses the SID task based on GMM-SVM in a three stage process. Firstly, the Gammatone Frequency Cepstral Coefficients (GFCC) and Mean Hilbert Envelope Coefficients (MHEC) of the speakers are extracted. Secondly, these features are modeled using Gaussian Mixture Model (GMM), on adapting the extracted acoustic features by mean, the corresponding super vectors are found and these vectors are trained using Support Vector Machine (SVM). Finally, the actual recognition is done by feeding the super vectors of them asked noisy test utterance by Ideal Binary Mask (IBM) into SVM model and their accuracy of recognition is compared for GFCC, MHEC and RASTA-MFCC in different noisy conditions. Findings: Evaluation results show that SID performance carried out with MHEC is extensively better than the performance of other two features. Applications: Major areas that implements automatic SIDs are forensics, surveillance and audio biometrics etc.

Sensitivity of automatic speaker identification to SVD digital audio watermarking

This paper proposes the utilization of SVD digital audio watermarking to increase the security of automatic speaker identification (ASI) systems and presents a study for the effect of watermarking on the ASI system performance. The SVD audio watermarking algorithm can be implemented on audio signals in time domain or in another appropriate transform domain and can be applied to the audio signal as a whole or on a segment-by-segment basis. The speaker recognition system works by generating a database of speaker's features using the MFCCs and polynomial shape coefficients extracted from each speaker after they are lexicographically ordered into 1-D signals. A matching process is performed for any new speaker to determine if he is belonging to the database or not, using a trained neural network. Experimental results show that the SVD audio watermarking doesn't degrade the ASI system performance severely. So, it can be used with ASI to increase security. Also, it was shown the segment by segment watermarking in the time domain achieves the highest detectability of the watermark. So, we can say that it is recommended to use SVD segment by segment audio watermarking with ASI systems implementing features extracted from the DCT or the DWT.

Acoustic feature extraction method for robust speaker identification

When there is a mismatch between the acoustic training environment and the testing environment, the performance of automatic speaker identification systems degrades significantly. A robust feature extraction method for speaker recognition based on the gammatone filter is therefore proposed in this paper. By employing the working mechanism of the human auditory model instead of the traditional triangular filter banks, gammatone filter banks are used to simulate the auditory model of the human ear cochlea. The cube root compression method, equal loudness technology, and relative spectral (RASTA) filtering technology are incorporated into the robust feature extraction process. A simulation experiment is conducted based on the Gaussian mixture model (GMM) recognition algorithm. The experimental results indicate that the proposed feature parameters could show superior robustness and represent the characteristics of the speaker better than the conventional mel-frequency cepstrum coefficient (MFCC), cochlear cepstrum coefficient (CFCC) and relative spectra-perceptual linear predictive (RASTA-PLP) parameters.

Acoustic analysis and feature transformation from neutral to whisper for speaker identification within whispered speech audio streams

Whispered speech is an alternative speech production mode from neutral speech, which is used by talkers intentionally in natural conversational scenarios to protect privacy and to avoid certain content from being overheard or made public. Due to the profound differences between whispered and neutral speech in vocal excitation and vocal tract function, the performance of automatic speaker identification systems trained with neutral speech degrades significantly. In order to better understand these differences and to further develop efficient model adaptation and feature compensation methods, this study first analyzes the speaker and phoneme dependency of these differences by a maximum likelihood transformation estimation from neutral speech towards whispered speech. Based on analysis results, this study then considers a feature transformation method in the training phase that leads to a more robust speaker model for speaker ID on whispered speech without using whispered adaptation data from test speakers. Three estimation methods that model the transformation from neutral to whispered speech are applied, including convolutional transformation (ConvTran), constrained maximum likelihood linear regression (CMLLR), and factor analysis (FA). a speech mode independent (SMI) universal background model (UBM) is trained using collected real neutral features and transformed pseudo-whisper features generated with the estimated transformation. Text-independent closed set speaker ID results using the UT-VocalEffort II corpus show performance improvement by using the proposed training framework. The best performance of 88.87% is achieved by using the ConvTran model, which represents a relative improvement of 46.26% compared to the 79.29% accuracy of the GMM-UBM baseline system. This result suggests that synthesizing pseudo-whispered speaker and background training data with the ConvTran model results in improved speaker ID robustness to whispered speech.

Modelling a Voice Activated Speaker Identification System using MFCC-Pitch-Formant Vector

The paper presents the model of an automatic speaker identification system which will recognize users based on their voice. The system will be relatively independent of spoken words but will rely on the voice quality of a user i.e. use speech independent voice recognition. The basic approach was to create a front end system which will identify speech parameters of particular users and create speech feature vectors which will later be used to train a back-propagation neural network for the recognition phase. Mel-frequency cepstrum coefficients and linear predictive coding coefficients have been used, along with Pitch and Formants, for feature extraction. The main area of focus of the paper is to outline the optimum set of speech features which form the most reliable model for an automatic speaker identification system.

Modulation Spectral Features for Robust Far-Field Speaker Identification

In this paper, auditory inspired modulation spectral features are used to improve automatic speaker identification (ASI) performance in the presence of room reverberation. The modulation spectral signal representation is obtained by first filtering the speech signal with a 23-channel gammatone filterbank. An eight-channel modulation filterbank is then applied to the temporal envelope of each gammatone filter output. Features are extracted from modulation frequency bands ranging from 3-15 H z and are shown to be robust to mismatch between training and testing conditions and to increasing reverberation levels. To demonstrate the gains obtained with the proposed features, experiments are performed with clean speech, artificially generated reverberant speech, and reverberant speech recorded in a meeting room. Simulation results show that a Gaussian mixture model based ASI system, trained on the proposed features, consistently outperforms a baseline system trained on mel-frequency cepstral coefficients. For multimicrophone ASI applications, three multichannel score combination and adaptive channel selection techniques are investigated and shown to further improve ASI performance.

Non-contemporary speech samples: auditory detectability of an 11 year delay and itseffect on automatic speaker identification

The need to compare non-contemporary speech samples is a common issue in forensic speaker recognition. Even if the size of the delay is known a crucial question has still to be
 answered in every single case: Is it possible that physiological aging or other factors have caused alterations of parameters of voice, speech and language to such a degree that the material basis for identification by human listeners and/or by automatic systems may no longer be regarded as adequate when a new identification task is due? Some studies on auditory speaker recognition suggest that, other variables being equal, a time lag of up to 6 years does not seem to pose a problem. To this author’s knowledge, the question has not yet been directed towards automatic identification systems. The present study uses speech
 data from ten male speakers recorded at intervals of 11 years and analyses the effect of the delay in terms of (a) the ability of different groups of listeners to detect it, and (b) its
 influence on the performance of an advanced automatic speaker identification system for forensic applications. Using contemporary samples for both ‘known’ and ‘unknown’
 models as a benchmark the automatic speaker identification system identified all speakers correctly with LRs between 102 and over 108. In the non-contemporary condition,
 where the older samples (i.e. ‘younger’ speakers) were used for the construction of models for ‘known’ and the samples recorded 11 years later for ‘unknown’ speakers, LRs of nine
 speakers remained unchanged or dropped only slightly. The LR for one speaker dropped sharply. It seems that this is the only case in which vocal aging, but perhaps also other
 time-related factors, may have played a rôle. The main conclusions of these experiments are that for most male speakers a delay of the size of a decade between voice samples will not pose a problem to either auditory or machine-based speaker identification.

Crime-detection speaker recognition system

Crime-detection automatic speaker verification and identification (CASVI) system oriented to nonprofessional experts was described at the 137th ASA Meeting [I. I. Gorban, N. I. Gorban, and A. V. Klimenko, J. Acoust. Soc. Am. 105, 1353 (1999)]. At the current meeting another speaker recognition system for professional crime-detection experts is presented. It consist of special units, Pentium-type computer, and programs realized speech-processing algorithms in automated and automatic modes. The system gives the possibility to research records made on different tape recorders, to fit tape speed, to decode speech records, to suppress noises, to correct frequency and nonline record distortions, to sort sounds, to measure and calculate different discriminate features, characteristics, and parameters usually used by crime-detection experts in their practical work, to compare the records, to form libraries and archives, and to make reports. The system has a simple and comfortable interface tailor-made for crime-detection expert aims. Police exploiting of the system has shown that utilization of the system raises productivity of expert work sometimes and essentially improves authenticity of phonoscope expertise.

Crime-detection automatic speaker verification and identification (CASVI) system

The crime-detection automatic speaker verification and identification (CASVI) system, using a new spectral and cepstral analysis technique, is described. Robust speaker recognition algorithms, the operation modes, the control windows, the testing methodology, and the testing results of the system are presented. Research of the system has shown it can efficiently work with strongly corrupted utterances, while the corruption of the utterances being compared may be considerably different. For any utterances, permissible frequency distortions are 35 dB in the operating band and the permissible signal-to-noise ratio of additive noise is 12 dB. In these conditions, the CASVI system using 12-s speech utterances demonstrates the possibility to verify and identify persons on the level of 90% of correct acceptance when the false-alarm rate is 10%. The verification and identification time by the system takes some minutes. The CASVI system does not require high qualification of an expert. The system has a very simple interface that allows working in full automatic mode and forming reports without any special schooling. The CASVI system is a software product installed on a Pentium-based PC running with Windows 95.

A COMBINED APPROACH TO TEXT-DEPENDENT SPEAKER IDENTIFICATION: COMPARISON WITH PURE NEURAL NET APPROACHES

A novel approach to automatic speaker identification (ASI) is presented. Most of the present automatic speaker identification systems based on neural networks have no definite mechanisms to compensate for time distortions due to elocution. Such models have less precise information about the intraspeaker measure. The new combined approach uses both distortion-based and discriminant-based methods. The distortion-based and discriminant-based methods are dynamic time warping (DTW) and artificial neural network (ANN) respectively. This paper compares this new classifier with a pure neural net classifier for speaker identification. The performance of the combined classifier surpasses that of a pure ANN classifier for the conditions tested.

Crime automatic speaker verification and identification system

A new automatic speaker verification process was presented at the Eighth Annual International Conference on Signal Processing Applications and Technology (ICSPAT ’97), San Francisco, CA (I. I. Gorban, Robust Speaker Verification Algorithms). On the basis of these algorithms the crime automatic speaker verification and identification (CASVI) system has been created. The main feature of the system is that it is possible to verify and identify a speaker when the speech records are very corrupted and/or contain extraneous noise. Testing conducted under different conditions has shown that the CASVI system works well when the level of frequency distortions is lower than 35 dB and the level of the signal-to-noise ratio is lower than 12 dB. These results have been obtained for a new modification of the algorithms in which the adaptive threshold verification process is included and the identification algorithms are added. A description of the CASVI system, it’s algorithms, the methodology, and the results of the system testing will also be presented at the meeting.