Social ambiance describes the context in which social interactions happen, and can be measured using speech audio by counting the number of concurrent speakers. This measurement has enabled various mental health tracking and human-centric IoT applications. While on-device Socal Ambiance Measure (SAM) is highly desirable to ensure user privacy and thus facilitate wide adoption of the aforementioned applications, the required computational complexity of state-of-the-art deep neural networks (DNNs) powered SAM solutions stands at odds with the often constrained resources on mobile devices. Furthermore, only limited labeled data is available or practical when it comes to SAM under clinical settings due to various privacy constraints and the required human effort, further challenging the achievable accuracy of on-device SAM solutions. To this end, we propose a dedicated neural architecture search framework for Energy-efficient and Real-time SAM (ERSAM). Specifically, our ERSAM framework can automatically search for DNNs that push forward the achievable accuracy vs. hardware efficiency frontier of mobile SAM solutions. For example, ERSAM-delivered DNNs only consume 40 mW • 12 h energy and 0.05 seconds processing latency for a 5 seconds audio segment on a Pixel 3 phone, while only achieving an error rate of 14.3% on a social ambiance dataset generated by LibriSpeech. We can expect that our ERSAM framework can pave the way for ubiquitous on-device SAM solutions which are in growing demand.

Exponential rise in wireless data demands is already creating a significant burden on current mobile networks. Meanwhile, the upcoming 5G system is believed to consist of heterogeneous access networks. The user satisfaction and radio resource efficiency are the main challenges for the network convergence. Network virtualization technology is regarded as an effective solution to above challenges. Heterogeneous networks are virtualized to multiple logical slices to best serve specific services. Two fundamental questions are how to virtualize mobile resources among different slices, and how to shield the impact of time-varying wireless channel on slicing with Quality of Service (QoS) guaranteed. In order to solve these two problems, we propose a two-timescale Virtualized Radio Resource Pre-Allocation mechanism, consisting of the inter-slice pre-allocation and the intra-slice scheduling. Specifically, the subcarrier and transmission power are jointly optimized and the base station coordination is also supported. For different network deployment scenarios, both the centralized and distributed solutions are provided. Simulation results demonstrate that both solutions are able to guarantee the QoS with the minimum requirements of radio resource.