Research on the Parameter Optimal Algorithm of Gaussian Mixture Model in Speaker Identification

In the statistical approach to offline handwritten numeral recognition, we use the Gaussian mixture model (GMM) to approximate arbitrary class conditional probability density. For simplification, the GMM is assumed to be diagonal covariance matrices. In the case of the features of handwritten numerals being correlated statistically, a large number of mixture components are usually needed to obtain a good approximation. To solve this problem, the feature vectors are first transformed to the space spanned by the eigenvectors of the covariance matrix so that the correlation among the elements is reduced, namely orthogonal transformation. This GMM is defined as orthogonal Gaussian mixture model (OGMM). Finally, the effectiveness of this algorithm is demonstrated by applying it to the NIST database.

Gaussian Mixture models is one of the most popular statistical methods in speaker recognition. The purpose of this research is to perform experiments of speaker recognition using various feature vectors: four formants, four formants with fundamental frequency and mel cepstrum coefficients. Gaussian mixture models using mel cepstrum coefficients is baseline in speaker recognition and gives one of the best results in text independent speaker recognition. After implementing experiments of speaker recognition and comparing experimental results we can affirm that mel scale cepstral coefficients and four formants with fundamental frequency gives quite the same recognition accuracy, but creating of Gaussian mixture speaker models and recognition process continues a few times longer using mel scale cepstral coefficients, because count of calculations is few times greater in that case. Using only four formants gives the worst results of recognition accuracy. Ill. 7, bibl. 12 (in English; summaries in English, Russian and Lithuanian).

Efficient similarity search for uncertain data is a challenging task in many modern data mining applications like image retrieval, speaker recognition and stock market analysis. A common way to model the uncertainty of data objects is using probability density functions in the form of Gaussian Mixture Models (GMMs), which have an ability to approximate arbitrary distribution. However, due to the possible unequal length of mixture models, the use of existing index techniques has serious problems for the objects modeled by GMMs. Either the techniques cannot handle GMMs or they have too many limitations. Hence, we propose a dynamic index structure, Gaussian Component based Index (GCI), for GMMs. GCI decomposes GMMs into the single, pairs, or n-lets of Gaussian components, stores these components into well studied index trees such as U-tree and Gauss-Tree, and refines the corresponding GMMs in a conservative but tight way. GCI supports both k-most-likely queries and probability threshold queries by means of Matching Probability. Extensive experimental evaluations of GCI demonstrate a considerable speed-up of similarity search on both synthetic and real-world data sets.

In speaker recognition, most of the computation originates from the likelihood computations between feature vectors of the unknown speaker and the models in the database. In this paper, we concentrate on optimizing Mel Frequency Cepstral Coefficient (MFCC) for feature extraction and Vector Quantization (VQ) for feature modeling. We reduce the number of feature vectors by pre-quantizing the test sequence prior to matching, and number of speakers by ruling out unlikely speakers during recognition process. The two important parameters, Recognition rate and minimized Average Distance between the samples, depends on the codebook size and the number of cepstral coefficients. We find, that this approach yields significant performance when the changes are made in the number of mfcc's and the codebook size. Recognition rate is found to reach upto 89% and the distortion reduced upto 69%.

This paper introduced an approach to design and implement an embedded SoPC (System on a Programmable Chip) technique with Altera Nios II processor for real-time speech recognition system by developing hardware/software with minimum usage of resources (hardware components) and relatively small size software to reduce memory utilization. This is achieved by using Mel Frequency Cepstral Coefficients (MFCCs) technique as speech signal feature extraction (observation vector). Using Gaussian Mixture Model (GMM) to model the observation vector of voice information. Finally, this model passed to the Hidden Markov Model (HMM) as probabilistic model to process the GMM statistically to make decision on utterance words recognition, whether a single or composite, one or more syllable words (i.e. one, six, target). The total framework was implemented on Altera Cyclone II EP2C70F896C6N FPGA chip sitting on ALTERA DE2-70 Development Board. The utility software which are used as tools for design and development hardware/software are Quartus II 11.0sp1 (32-Bit) and Nios II 11.0spl IDE/C++ respectively. Each word model (template) stored as Transition Matrix, Diagonal Covariance Matrices, and Mean Vectors in the system memory. Each word model utilizes only 4.45Kbytes regardless of the spoken word length. Accuracy of the recognition words (digit/0 to digit/10) given 100% for the individual speaker. Training and recognition software has size (code + initialized data) equal to 312Kbytes.

Channel interference factor for the identification result is prevalent among the existing speaker recognition algorithms. In order to improve the accuracy of the algorithm, the paper utilizes the technique of latent factor analysis(LFA) to deal with the channel factors in the speaker's Gaussian Mixture Model(GMM). In the endpoint detection phase of speaker recognition, the algorithm introduces the GMM for speech modeling to accurately determine the beginning and ending points of the speech segment, and then establish speaker GMM. The algorithm use factor analysis technique to fit the differences between the speaker characteristics space and the channel space, and removes channel factor in speaker's GMM. And then the algorithm extracts GMM super-vectors as the input of Support Vector Machine(SVM) to obtain recognition results. Experimental results show that the combination of factor analysis and SVM can obtain better recognition rate and ensure the robustness of the recognition algorithm.

Speaker identification identifies the speaker among a set of users by matching against a set of voiceprints. In speaker identification, the identification time depends on the number of feature vectors, their dimensionality and the number of speakers. In this paper, text independent speaker identification model is developed by taking in MFCCs with VQ to obtain pressed feature vectors without losing much information, and the numbers of speakers are reduced in the test by gender detection algorithm. Gaussian Mixture Model (GMM) is used a modeling technique. Results show that proposed approach always yields better improvements in accuracy and brings almost 50% reduces in time processing.

This article proposes the distribution similarity measure–based Gaussian mixtures model for the contact-state (CS) modelling in force-guided robotic assembly processes of flexible rubber parts. The wrench (Cartesian force and torque) signals of the manipulated object are captured for different states of the given assembly process. The distribution similarity measure–based Gaussian mixtures model CS modelling scheme is employed in modelling the captured wrench signals for different CSs. The proposed distribution similarity measure–based Gaussian mixtures model CS modelling scheme uses the Gaussian mixtures model in modelling the captured signals. The parameters of the Gaussian mixtures models are computed using expectation maximisation. The optimal number of Gaussian mixtures model components for each CS model is determined by considering the classification success rate as an index for the similarity measure between the distribution of the captured signals and the developed models. The optimal number of Gaussian mixtures model components corresponds to the highest classification success rate; hence, object elasticity variation would be accommodated by properly choosing the optimal number of Gaussian mixtures model components. The performance of the proposed distribution similarity measure–based Gaussian mixtures model CS modelling strategy is evaluated by a test stand composed of a KUKA lightweight robot doing peg-in-hole assembly processes for flexible rubber objects. Two rubber objects with different elasticity are considered for two experiments; in the first experiment, an elastic peg of 30 Shore A hardness is considered and that of the second experiment has hardness of 6 Shore A which is even softer than the one used in experiment 1. Employing the proposed distribution similarity measure–based Gaussian mixtures model CS modelling strategy excellent classification success rate was obtained for both experiments. However, more Gaussian mixtures model components are required for the softer one that gives a strong impression of the non-stationarity behaviour increment for softer materials. Comparison is performed with the available CS modelling schemes and the distribution similarity measure–based Gaussian mixtures model is shown to provide the best classification success rate performance with a reduced computational time.

Speech applications, which operate a system by voice commands, facilitate web access for disabled and visually impaired users. Human-computer interactions, such as speaking and listening to web applications, provide options for developing a multimodal interaction tool in the accessible design of an intelligent web. Speaker identification and verification are essential functionalities for intelligent web programs with speech applications. This paper proposes an enhanced Gaussian mixture model (GMM) method by incorporating the information derived from the support vector machine (SVM), called EGMM-SVM, for web-based applications with speaker recognition. The EGMM-SVM improves the accuracy of the estimated likelihood scores between the speech frame and the GMM. In EGMM-SVM, SVM plays a crucial role in transmitting the quality information of the utterances from a test speaker, through the GMM when performing GMM likelihood calculations. The experimental results show that speaker recognition by using the developed EGMM-SVM with an accurate operation mechanism for Gaussian distribution derivations yields a higher recognition rate than does a conventional GMM without any considerations on the quality of test speech utterances.

In the biometrics community, face and speaker recognition are mature fields in which several systems have been proposed over the past twenty years. While existing systems perform well under controlled recording conditions, mismatch caused by the use of different sensors or a lack of cooperation from the subject still significantly affects performance, especially in challenging scenarios such as in forensics. Furthermore, existing methods suffer from scalability issues, which prevents them from taking advantage of increasingly large amounts of training data. This is otherwise a promising approach to improve accuracy in such challenging scenarios. In this thesis we address these problems of mismatch and complexity by developing scalable probabilistic models that we apply to face, speaker and bimodal recognition. Our contributions are four-fold. First, we propose a unified framework for session variability modeling techniques based on Gaussian mixture models (GMM), that encompasses inter-session variability (ISV) modeling, joint factor analysis (JFA) and total variability (TV) modeling. Second, we propose a novel exact and scalable formulation of probabilistic linear discriminant analysis (PLDA), which is a probabilistic and generative framework that models between-class and within-class variations. This formulation solves a major scalability issue, by improving both the time complexity of the training procedure from cubic to linear with respect to the number of samples per class, and the complexity of the scoring procedure. Furthermore, the implementations of all the proposed techniques are integrated into a novel collaborative open source software library called Bob 1 that enforces fair evaluations and encourages reproducible research. Fourth and finally, large-scale experiments are conducted with all of the above machine learning algorithms on several databases such as FRGC for face recognition, NIST SRE12 for speaker recognition and MOBIO for bimodal recognition, showing competitive performances.

Exploring similarity-based classification of larynx disorders from human voice

Relevance factor of maximum a posteriori adaptation for GMM–NAP–SVM in speaker and language recognition

Purpose:Xerostomia (dry mouth), secondary to parotid‐gland injury, is a distressing side‐effect in head‐and‐neck radiotherapy (RT). This study's purpose is to develop a novel ultrasound technique to quantitatively evaluate post‐RT parotid‐gland injury.Methods:Recent ultrasound studies have shown that healthy parotid glands exhibit homogeneous echotexture, whereas post‐RT parotid glands are often heterogeneous, with multiple hypoechoic (inflammation) or hyperechoic (fibrosis) regions. We propose to use a Gaussian mixture model to analyze the ultrasonic echo‐histogram of the parotid glands. An IRB‐approved clinical study was conducted: (1) control‐group: 13 healthy‐volunteers, served as the control; (2) acutetoxicity group − 20 patients (mean age: 62.5 ± 8.9 years, follow‐up: 2.0±0.8 months); and (3) late‐toxicity group − 18 patients (mean age: 60.7 ± 7.3 years, follow‐up: 20.1±10.4 months). All patients experienced RTOG grade 1 or 2 salivary‐gland toxicity. Each participant underwent an ultrasound scan (10 MHz) of the bilateral parotid glands. An echo‐intensity histogram was derived for each parotid and a Gaussian mixture model was used to fit the histogram using expectation maximization (EM) algorithm. The quality of the fitting was evaluated with the R‐squared value.Results:(1) Controlgroup: all parotid glands fitted well with one Gaussian component, with a mean intensity of 79.8±4.9 (R‐squared>0.96). (2) Acute‐toxicity group: 37 of the 40 post‐RT parotid glands fitted well with two Gaussian components, with a mean intensity of 42.9±7.4, 73.3±12.2 (R‐squared>0.95). (3) Latetoxicity group: 32 of the 36 post‐RT parotid fitted well with 3 Gaussian components, with mean intensities of 49.7±7.6, 77.2±8.7, and 118.6±11.8 (R‐squared>0.98).Conclusion:RT‐associated parotid‐gland injury is common in head‐and‐neck RT, but challenging to assess. This work has demonstrated that the Gaussian mixture model of the echo‐histogram could quantify acute and late toxicity of the parotid glands. This study provides meaningful preliminary data from future observational and interventional clinical research.

The Gaussian mixture models (GMM) represent an efficient model that was broadly used in most of speaker recognition applications. This study introduces a novel method for speaker verification task. We propose a reduced feature vector employing new information detected from the speaker's voice for performing text-independent speaker verification applications using GMM. We use the power spectrum density of the speech signal to improve the system's performance. Speaker verification experiments were evaluated with the TIMIT dataset. The suggested system performance is evaluated against the baseline systems. The decrease in the error rate is well observed and the results have demonstrated the effectiveness of the new approach which avoids the use of more complex algorithms or the combination of different approaches.

With rapid developments in techniques related to the internet of things, smart service applications such as voice-command-based speech recognition and smart care applications such as context-aware-based emotion recognition will gain much attention and potentially be a requirement in smart home or office environments. In such intelligence applications, identity recognition of the specific member in indoor spaces will be a crucial issue. In this study, a combined audio-visual identity recognition approach was developed. In this approach, visual information obtained from face detection was incorporated into acoustic Gaussian likelihood calculations for constructing speaker classification trees to significantly enhance the Gaussian mixture model (GMM)-based speaker recognition method. This study considered the privacy of the monitored person and reduced the degree of surveillance. Moreover, the popular Kinect sensor device containing a microphone array was adopted to obtain acoustic voice data from the person. The proposed audio-visual identity recognition approach deploys only two cameras in a specific indoor space for conveniently performing face detection and quickly determining the total number of people in the specific space. Such information pertaining to the number of people in the indoor space obtained using face detection was utilized to effectively regulate the accurate GMM speaker classification tree design. Two face-detection-regulated speaker classification tree schemes are presented for the GMM speaker recognition method in this study—the binary speaker classification tree (GMM-BT) and the non-binary speaker classification tree (GMM-NBT). The proposed GMM-BT and GMM-NBT methods achieve excellent identity recognition rates of 84.28% and 83%, respectively; both values are higher than the rate of the conventional GMM approach (80.5%). Moreover, as the extremely complex calculations of face recognition in general audio-visual speaker recognition tasks are not required, the proposed approach is rapid and efficient with only a slight increment of 0.051 s in the average recognition time.