7UDGLWLRQDOO\ 4R6 KDV EHHQ DGGUHVVHG E\ XVLQJ network measurements (e.g., loss rates and delays), and little attention has been paid to the quality perceived by end-users of the applications running over the network. Here, we address the issue of integrating speech quality subjective scores and network parameters measurements, for designing control algorithms that would yield the best QoS that could be delivered under a given communications network situation. First, we build a neural network based automaton to measure speech quality in real time, at the style of a group of human subjects when participating in an MOS test. We consider the effects of changes in network parameters (e.g., packetization interval, packet loss rate and their pattern distribution) and encoding on speech signals transmitted over the network. Our database includes transmitted speech signals in different languages. Then, we outline a control mechanism which, based on the application performance within a session (i.e., MOS speech quality scores generated by the neural networks), dynamically adjusts parameters (codec and packetization interval). Finally, we analyze preliminary results to show two main benefits: first, a better use of bandwidth, and second, delivery of the best possible speech quality given the network current situation.
Index Terms9RLFH RYHU ,3 3DFNHW 6ZLWFKHG 1HWZRUNV Speech Quality Assessment, Neural Networks and End-to-End Control Mechanisms.
An in-depth understanding and dynamic modeling of the relationship a robot has with its environment (i.e., the overall ecology) is important to ensure that fielded robotic systems are:Not competing with other agents that can do the task more effectively and hence prove themselves useless.Successful competitors within the ecological system and can potentially displace less efficient agents.Ecologically sensitive so that agent-environmental system dynamics are well-modeled and as predictable as possible whenever new robotic technology is introduced.Little emphasis to date has been placed on this ecological approach within mobile robotics research, although some related research has been conducted in the recent past in tile context of the artificial life community. All too often, however, these approaches lack both a strong biological basis for their working assumptions and any formal underpinnings (neural, behavioral, and computational) for the results they obtain. We address these problems directly using schema theory and neurophysiological and ethological models to provide credible, generalizable, and useful results in this domain. These systems are currently grounded in robotic simulations and ultimately in actual robotic hardware.The study of sensory guided behaviors in living animals has become of general significance not only for scientists working in neuroscience and computational neuroscience but also for scientists working in robotics and distributed artificial intelligence, who are using functional principles generated from the study of living animals as models to build computer based automata that display complex sensorimotor behaviors. Our research effort, which follows these lines, is tied together by software tools including: NSL, a neural simulation language; ASL, an abstract schema language; and MissionLab, a schema-based mission-oriented simulation and robot implementation environment.
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.