Selecting the optimal cloud target to migrate SQL estates from on-premises to the cloud remains a challenge. Current solutions are not only time-consuming and error-prone, requiring significant user input, but also fail to provide appropriate recommendations. We present Doppler, a scalable recommendation engine that provides right-sized Azure SQL Platform-as-a-Service (PaaS) recommendations without requiring access to sensitive customer data and queries. Doppler introduces a novel price-performance methodology that allows customers to get a personalized rank of relevant cloud targets solely based on low-level resource statistics, such as latency and memory usage. Doppler supplements this rank with internal knowledge of Azure customer behavior to help guide new migration customers towards one optimal target. Experimental results over a 9-month period from prospective and existing customers indicate that Doppler can identify optimal targets and adapt to changes in customer workloads. It has also found cost-saving opportunities among over-provisioned cloud customers, without compromising on capacity or other requirements. Doppler has been integrated and released in the Azure Data Migration Assistant v5.5, which receives hundreds of assessment requests daily.

Audio-based cough detection has become more pervasive in recent years because of its utility in evaluating treatments and the potential to impact the quality of life for individuals with chronic cough. We critically examine the current state of the art in cough detection, concluding that existing approaches expose private audio recordings of users and bystanders. We present a novel algorithm for detecting coughs from the audio stream of a mobile phone. Our system allows cough sounds to be reconstructed from the feature set, but prevents speech from being reconstructed intelligibly. We evaluate our algorithm on data collected in the wild and report an average true positive rate of 92% and false positive rate of 0.5%. We also present the results of two psychoacoustic experiments which characterize the tradeoff between the fidelity of reconstructed cough sounds and the intelligibility of reconstructed speech.

Recently we began using Amazon Mechanical Turk (AMT), an Internet marketplace, to deploy our spoken dialogue systems to large audiences for user testing and data collection purposes. This crowdsourcing method of collecting data contrasts with the time- and labor- intensive developer annotation methods. In this paper, we compare these data in various combinations with traditionally-collected corpora for training our speech recognizer's language model. Our results show that AMT text queries are effective for initial language model training for spoken dialogue systems, and that crowd-sourced speech collection within the context of a spoken dialogue framework provides significant improvement.

Trees and graphs are relevant to many online tasks such as visualizing social networks, product catalogs, educational portals, digital libraries, the semantic web, concept maps and personalized information management. SpicyNodes is an information-visualization technology that builds upon existing research on radial tree layouts and graph structures. Users can browse a tree, clicking from node to node, as well as successively viewing a node, immediately related nodes and the path back to the ""home" nodes. SpicyNodes' layout algorithms maintain balanced layouts using a hybrid mixture of a geometric layout (a succession of spanning radial trees) and force-directed layouts to minimize overlapping nodes, plus several other improvements over prior art. It provides XML-based API and GUI authoring tools. The goal of the SpicyNodes project is to implement familiar principles of radial maps and focus+context with an attractive and inviting look and feel in an open system that is accessible to virtually any Internet user.