arXiv subjects

Sara Khalifa

Publications and source records attributed to Sara Khalifa.

23 records · Page 2Linked to original sources

arXiv2020

Multi-Task Semi-Supervised Adversarial Autoencoding for Speech Emotion Recognition

Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the scarcity of emotion datasets, which is a challenge for developing any robust machine learning model in general. In this paper, we propose a solution to this problem: a multi-task learning framework that uses auxiliary tasks for which data is abundantly available. We show that utilisation of this additional data can improve the primary task of SER for which only limited labelled data is available. In particular, we use gender identifications and speaker recognition as auxiliary tasks, which allow the use of very large datasets, e.g., speaker classification datasets. To maximise the benefit of multi-task learning, we further use an adversarial autoencoder (AAE) within our framework, which has a strong capability to learn powerful and discriminative features. Furthermore, the unsupervised AAE in combination with the supervised classification networks enables semi-supervised learning which incorporates a discriminative component in the AAE unsupervised training pipeline. This semi-supervised learning essentially helps to improve generalisation of our framework and thus leads to improvements in SER performance. The proposed model is rigorously evaluated for categorical and dimensional emotion, and cross-corpus scenarios. Experimental results demonstrate that the proposed model achieves state-of-the-art performance on two publicly available datasets.

cs.SD↗

arXiv2020

Towards Optimal Kinetic Energy Harvesting for the Batteryless IoT

Traditional Internet of Things (IoT) sensors rely on batteries that need to be replaced or recharged frequently which impedes their pervasive deployment. A promising alternative is to employ energy harvesters that convert the environmental energy into electrical energy. Kinetic Energy Harvesting (KEH) converts the ambient motion/vibration energy into electrical energy to power the IoT sensor nodes. However, most previous works employ KEH without dynamically tracking the optimal operating point of the transducer for maximum power output. In this paper, we systematically analyse the relation between the operating point of the transducer and the corresponding energy yield. To this end, we explore the voltage-current characteristics of the KEH transducer to find its Maximum Power Point (MPP). We show how this operating point can be approximated in a practical energy harvesting circuit. We design two hardware circuit prototypes to evaluate the performance of the proposed mechanism and analyse the harvested energy using a precise load shaker under a wide set of controlled conditions typically found in human-centric applications. We analyse the dynamic current-voltage characteristics and specify the relation between the MPP sampling rate and harvesting efficiency which outlines the need for dynamic MPP tracking. The results show that the proposed energy harvesting mechanism outperforms the conventional method in terms of generated power and offers at least one order of magnitude higher power than the latter.

eess.SP↗

arXiv2020

Towards Energy Positive Sensing using Kinetic Energy Harvesters

Conventional systems for motion context detection rely on batteries to provide the energy required for sampling a motion sensor. Batteries, however, have limited capacity and, once depleted, have to be replaced or recharged. Kinetic Energy Harvesting (KEH) allows to convert ambient motion and vibration into usable electricity and can enable batteryless, maintenance free operation of motion sensors. The signal from a KEH transducer correlates with the underlying motion and may thus directly be used for context detection, saving space, cost and energy by omitting the accelerometer. Previous work uses the open circuit or the capacitor voltage for sensing without using the harvested energy to power a load. In this paper, we propose to use other sensing points in the KEH circuit that offer information rich sensing signals while the energy from the harvester is used to power a load. We systematically analyse multiple sensing signals available in different KEH architectures and compare their performance in a transport mode detection case study. To this end, we develop four hardware prototypes, conduct an extensive measurement campaign and use the data to train and evaluate different classifiers. We show that sensing the harvesting current signal from a transducer can be energy positive, delivering up to ten times as much power as it consumes for signal acquisition, while offering comparable detection accuracy to the accelerometer signal for most of the considered transport modes.

eess.SP↗

arXiv2019

Pre-training in Deep Reinforcement Learning for Automatic Speech Recognition

Deep reinforcement learning (deep RL) is a combination of deep learning with reinforcement learning principles to create efficient methods that can learn by interacting with its environment. This led to breakthroughs in many complex tasks that were previously difficult to solve. However, deep RL requires a large amount of training time that makes it difficult to use in various real-life applications like human-computer interaction (HCI). Therefore, in this paper, we study pre-training in deep RL to reduce the training time and improve the performance in speech recognition, a popular application of HCI. We achieve significantly improved performance in less time on a publicly available speech command recognition dataset.

cs.SD↗

arXiv2019

EnTrans:Leveraging Kinetic Energy Harvesting Signal for Transportation Mode Detection

Monitoring the daily transportation modes of an individual provides useful information in many application domains, such as urban design, real-time journey recommendation, as well as providing location-based services. In existing systems, accelerometer and GPS are the dominantly used signal sources for transportation context monitoring which drain out the limited battery life of the wearable devices very quickly. To resolve the high energy consumption issue, in this paper, we present EnTrans, which enables transportation mode detection by using only the kinetic energy harvester as an energy-efficient signal source. The proposed idea is based on the intuition that the vibrations experienced by the passenger during traveling with different transportation modes are distinctive. Thus, voltage signal generated by the energy harvesting devices should contain sufficient features to distinguish different transportation modes. We evaluate our system using over 28 hours of data, which is collected by eight individuals using a practical energy harvesting prototype. The evaluation results demonstrate that EnTrans is able to achieve an overall accuracy over 92% in classifying five different modes while saving more than 34% of the system power compared to conventional accelerometer-based approaches.

cs.HC↗