Speech emotion recognition (SER) plays a significant role in human–machine interaction. Emotion recognition from speech and its precise classification is a challenging task because a machine is unable to understand its context. For an accurate emotion classification, emotionally relevant features must be extracted from the speech data. Traditionally, handcrafted features were used for emotional classification from speech signals; however, they are not efficient enough to accurately depict the emotional states of the speaker. In this study, the benefits of a deep convolutional neural network (DCNN) for SER are explored. For this purpose, a pretrained network is used to extract features from state-of-the-art speech emotional datasets. Subsequently, a correlation-based feature selection technique is applied to the extracted features to select the most appropriate and discriminative features for SER. For the classification of emotions, we utilize support vector machines, random forests, the k-nearest neighbors algorithm, and neural network classifiers. Experiments are performed for speaker-dependent and speaker-independent SER using four publicly available datasets: the Berlin Dataset of Emotional Speech (Emo-DB), Surrey Audio Visual Expressed Emotion (SAVEE), Interactive Emotional Dyadic Motion Capture (IEMOCAP), and the Ryerson Audio Visual Dataset of Emotional Speech and Song (RAVDESS). Our proposed method achieves an accuracy of 95.10% for Emo-DB, 82.10% for SAVEE, 83.80% for IEMOCAP, and 81.30% for RAVDESS, for speaker-dependent SER experiments. Moreover, our method yields the best results for speaker-independent SER with existing handcrafted features-based SER approaches.
Network-on-chip (NoC) is evolving as a better substitute for incorporating a large number of cores on a single system-on-chip (SoC). The dependency on multi-core systems to accomplish the highperformance constraints of composite embedded applications is on the rise. This leads to the realization of efficient mapping approaches for such complex applications. The significance of efficient application mapping approaches has increased ever since the embedded applications have become more complex and performance-oriented. This paper presents the detailed comparative analysis and categorization of application mapping approaches with current trends in NoC design implementation. These approaches target to improve the performance of the whole system by optimizing communication cost, energy, power consumption, and latency. Apart from the categorization of the discussed approaches, comparison of communication cost, power, energy, and latency of the NoC system carried out on real applications like VOPD and MPEG4. Moreover, the best technique identified in each category based on the evaluation of performance results. INDEX TERMS Network-on-Chip, application mapping, NoC design, VOPD, System-on-Chip. I. INTRODUCTION System-on-Chip (SoC) is an archetype for the design and implementation of on-chip circuits that can support multiple systems on a single chip. The ever-rising number of processing cores on a single chip has made the efficiency of onchip designs as one of the major aspects in evaluating the average performance of embedded SoC. To fulfill the performance needs and to provide flexibility in the designs the field of Network on Chip (NoC) has emerged that separates the communication from the computation. Many surveys [1]-[7] are published in general and textbooks are also available on the topic [8]-[10]. There is still a need to solve more advanced research problems in NoC. Application mapping on NoC architecture has a prominent place among all the research problems which can be arbitrated from the published The associate editor coordinating the review of this manuscript and approving it for publication was Eyuphan Bulut. papers and current trends. This survey assumes a textbooklevel acquaintance of NoC terminology. The aim is to provide a comprehensive overview of all the aspects of application mapping (task graph generation, scheduling, optimization techniques, simulation setup, and performance evaluation metrics). The organization of this survey is as follows; first, we provide the reader the need and overview of application mapping in NoC presented in Section I. A detailed review and calcification of application mapping techniques in NoCs are discussed in Section II. The current and latest trends in application mapping are summarized in Section III. In Section IV performance comparison and the points that can create the difference between these techniques are highlighted. Finally, Section VI concludes this paper. A. MOTIVATION AND SCOPE Mostly synthetic traffic patterns are used to imitate the functionalities of rea...
The advent of new devices, technology, machine learning techniques, and the availability of free large speech corpora results in rapid and accurate speech recognition. In the last two decades, extensive research has been initiated by researchers and different organizations to experiment with new techniques and their applications in speech processing systems. There are several speech command based applications in the area of robotics, IoT, ubiquitous computing, and different human-computer interfaces. Various researchers have worked on enhancing the efficiency of speech command based systems and used the speech command dataset. However, none of them catered to noise in the same. Noise is one of the major challenges in any speech recognition system, as real-time noise is a very versatile and unavoidable factor that affects the performance of speech recognition systems, particularly those that have not learned the noise efficiently. We thoroughly analyse the latest trends in speech recognition and evaluate the speech command dataset on different machine learning based and deep learning based techniques. A novel technique is proposed for noise robustness by augmenting noise in training data. Our proposed technique is tested on clean and noisy data along with locally generated data and achieves much better results than existing state-of-the-art techniques, thus setting a new benchmark.
Computer-Aided Language Learning (CALL) is growing nowadays because learning new languages is essential for communication with people of different linguistic backgrounds. Mispronunciation detection is an integral part of CALL, which is used for automatic pointing of errors for the non-native speaker. In this paper, we investigated the mispronunciation detection of Arabic words using deep Convolution Neural Network (CNN). For automated pronunciation error detection, we proposed CNN features-based model and extracted features from different layers of Alex Net (layers 6, 7, and 8) to train three machine learning classifiers; K-nearest neighbor (KNN), Support Vector Machine (SVM) and Random Forest (RF). We also used a transfer learning-based model in which feature extraction and classification are performed automatically. To evaluate the performance of the proposed method, a comprehensive evaluation is provided on these methods with a traditional machine learning-based method using Mel Frequency Cepstral Coefficients (MFCC) features. We used the same three classifiers KNN, SVM, and RF in the baseline method for mispronunciation detection. Experimental results show that with handcrafted features, transfer learning-based method and classification based on deep features extracted from Alex Net achieved an average accuracy of 73.67, 85 and 93.20 on Arabic words, respectively. Moreover, these results reveal that the proposed method with feature selection achieved the best average accuracy of 93.20% than all other methods.
Aggressive scaling in deep nanometer technology enables chip multiprocessor design facilitated by the communication-centric architecture provided by Network-on-Chip (NoC). At the same time, it brings considerable challenges in reliability because a fault in the network architecture severely impacts the performance of a system. To deal with these reliability challenges, this research proposed NoCGuard, a reconfigurable architecture designed to tolerate multiple permanent faults in each pipeline stage of the generic router. NoCGuard router architecture uses four highly reliable and low-cost fault-tolerant strategies. We exploited resource borrowing and double routing strategy for the routing computation stage, default winner strategy for the virtual channel allocation stage, runtime arbiter selection and default winner strategy for the switch allocation stage and multiple secondary bypass paths strategy for the crossbar stage. Unlike existing reliable router architectures, our architecture features less redundancy, more fault tolerance, and high reliability. Reliability comparison using Mean Time to Failure (MTTF) metric shows 5.53-time improvement in a lifetime and using Silicon Protection Factor (SPF), 22-time improvement, which is better than state-of-the-art reliable router architectures. Synthesis results using 15 nm and 45 nm technology library show that additional circuitry incurs an area overhead of 28.7% and 28% respectively. Latency analysis using synthetic, PARSEC and SPLASH-2 traffic shows minor increase in performance by 3.41%, 12% and 15% respectively while providing high reliability.Electronics 2020, 9, 342 2 of 22 design and has led to the evolution of on-chip interconnection network or network-on-chip (NoC) [3,4]. NoC architecture is a packet-based inter-connected network that separates communication from the computation. As it is different from the shared bus, it facilitates customization in terms of bandwidth, buffers size, and topology. It offers scalability without using long global wires. NoC infrastructure consists of routers and links that are used to deliver packets via layered protocol [5].The continuous improvement in process technology yields higher transistor density [1]. It makes transistors and links more vulnerable to different fault mechanisms [6,7]. A fault in a transistor may lead to erroneous computation. Open/short circuit in links, result in data corruption. Even single fault can paralyze the whole chip. Primarily, faults are classified into permanent and transient categories [8]. Permanent faults are also known as hard faults, apparent in the chip for a lifetime after their occurrence. They permanently affect the functionality of the chip. They are traditionally caused by open/short circuits in links, time-dependent-dielectric-breakdown (TDDB) [9], electro-migration (EM) [10], stress migration, negative-bias-temperature-instability (NBTI) [11], hot carrier injection [12] and thermal cycling [13]. On the other hand, transient faults, also known as soft errors, occur only for on...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.