A. Manisha

Bio: A. Manisha is an academic researcher from VIT University. The author has contributed to research in topics: k-nearest neighbors algorithm & Support vector machine. The author has an hindex of 1, co-authored 1 publications receiving 9 citations.

A text-independent speaker verification model: A comparative analysis

Abstract: The most pressing challenge in the field of voice biometrics is selecting the most efficient technique of speaker recognition. Every individual's voice is peculiar, factors like physical differences in vocal organs, accent and pronunciation contributes to the problem's complexity. In this paper, we explore the various methods available in each block in the process of speaker recognition with the objective to identify best of techniques that could be used to get precise results. We study the results on text independent corpora. We use MFCC (Mel-frequency cepstral coefficient), LPCC (linear predictive cepstral coefficient) and PLP (perceptual linear prediction) algorithms for feature extraction, PCA (Principal Component Analysis) and t-SNE for dimensionality reduction and SVM (Support Vector Machine), feed forward, nearest neighbor and decision tree algorithms for classification block in speaker recognition system and comparatively analyze each block to determine the best technique.

Multimodal Biometrics for Enhanced IoT Security

Abstract: Biometric authentication is a promising approach to securing the Internet of Things (IoT). Although existing research shows that using multiple biometrics for authentication helps increase recognition accuracy, the majority of biometric approaches for IoT today continue to rely on a single modality. We propose a multimodal biometric approach for IoT based on face and voice modalities that is designed to scale to the limited resources of an IoT device. Our work builds on the foundation of Gofman et al. [7] in implementing face and voice feature-level fusion on mobile devices. We used discriminant correlation analysis (DCA) to fuse features from face and voice and used the K-nearest neighbors (KNN) algorithm to classify the features. The approach was implemented on the Raspberry Pi IoT device and was evaluated on a dataset of face images and voice files acquired using a Samsung Galaxy S5 device in real-world conditions such as dark rooms and noisy settings. The results show that fusion increased recognition accuracy by 52.45% compared to using face alone and 81.62% compared to using voice alone. It took an average of 1.34 seconds to enroll a user and 0.91 seconds to perform the authentication. To further optimize execution speed and reduce power consumption, we implemented classification on a field-programmable gate array (FPGA) chip that can be easily integrated into an IoT device. Experimental results showed that the proposed FPGA-accelerated KNN could achieve 150x faster execution time and 12x lower energy consumption compared to a CPU.

Survey of biometric pattern recognition via machine learning techniques

Abstract: Biometrics, as a computer science field, can be understood as the discipline that study how to generate computer models of the physical (e.g. hand geometry, fingerprints, iris and so on) and behavioral (e.g. signature; a kind of behavior pattern) characteristics of the human being for single or several individuals identification. Usually, these characteristics are used to provide authentication information for security systems. However, some of these characteristics are hard to obtain in a properly way and it is necessary to use several algorithms both to process them and to use them on a security systems. In this sense, in this paper it is presented an overview of some Machine Learning approaches for biometric pattern recognition.

Finding Meanings in Low Dimensional Structures: Stochastic Neighbor Embedding Applied to the Analysis of Indri indri Vocal Repertoire.

Abstract: Although there is a growing number of researches focusing on acoustic communication, the lack of shared analytic approaches leads to inconsistency among studies. Here, we introduced a computational method used to examine 3360 calls recorded from wild indris (Indri indri) from 2005–2018. We split each sound into ten portions of equal length and, from each portion we extracted spectral coefficients, considering frequency values up to 15,000 Hz. We submitted the set of acoustic features first to a t-distributed stochastic neighbor embedding algorithm, then to a hard-clustering procedure using a k-means algorithm. The t-distributed stochastic neighbor embedding (t-SNE) mapping indicated the presence of eight different groups, consistent with the acoustic structure of the a priori identification of calls, while the cluster analysis revealed that an overlay between distinct call types might exist. Our results indicated that the t-distributed stochastic neighbor embedding (t-SNE), successfully been employed in several studies, showed a good performance also in the analysis of indris’ repertoire and may open new perspectives towards the achievement of shared methodical techniques for the comparison of animal vocal repertoires.

Speeding up training of automated bird recognizers by data reduction of audio features.

Abstract: Automated acoustic recognition of birds is considered an important technology in support of biodiversity monitoring and biodiversity conservation activities. These activities require processing large amounts of soundscape recordings. Typically, recordings are transformed to a number of acoustic features, and a machine learning method is used to build models and recognize the sound events of interest. The main problem is the scalability of data processing, either for developing models or for processing recordings made over long time periods. In those cases, the processing time and resources required might become prohibitive for the average user. To address this problem, we evaluated the applicability of three data reduction methods. These methods were applied to a series of acoustic feature vectors as an additional postprocessing step, which aims to reduce the computational demand during training. The experimental results obtained using Mel-frequency cepstral coefficients (MFCCs) and hidden Markov models (HMMs) support the finding that a reduction in training data by a factor of 10 does not significantly affect the recognition performance.

Intelligent Instruction-Based IoT Framework for Smart Home Applications using Speech Recognition

Abstract: Design of a smart home using Internet of Things (IoT) and Machine Learning technology has been presented in this paper. This design is primarily based on LoRaWAN protocol and the main objective of this work was to establish an IoT network that is based on integration of sensors, gateway, network server and data visualization system. More importantly, intelligent speech recognition system is designed and presented here in detail as part of this work to achieve a novel futuristic smart home system design framework with intelligent instruction-based operation mechanism. In the case of low noise, the success rate of speaker recognition is above 90% based on THCHS-30 dataset.