Adversarial attacks against commercial black-box speech platforms, including cloud speech APIs and voice control devices, have received little attention until recent years. The current "black-box" attacks all heavily rely on the knowledge of prediction/confidence scores to craft effective adversarial examples, which can be intuitively defended by service providers without returning these messages. In this paper, we propose two novel adversarial attacks in more practical and rigorous scenarios. For commercial cloud speech APIs, we propose Occam, a decision-only black-box adversarial attack, where only final decisions are available to the adversary. In Occam, we formulate the decision-only AE generation as a discontinuous large-scale global optimization problem, and solve it by adaptively decomposing this complicated problem into a set of sub-problems and cooperatively optimizing each one. Our Occam is a one-size-fits-all approach, which achieves 100% success rates of attacks with an average SNR of 14.23dB, on a wide range of popular speech and speaker recognition APIs, including Google, Alibaba, Microsoft, Tencent, iFlytek, and Jingdong, outperforming the state-of-the-art black-box attacks. For commercial voice control devices, we propose NI-Occam, the first non-interactive physical adversarial attack, where the adversary does not need to query the oracle and has no access to its internal information and training data. We combine adversarial attacks with model inversion attacks, and thus generate the physically-effective audio AEs with high transferability without any interaction with target devices. Our experimental results show that NI-Occam can successfully fool Apple Siri, Microsoft Cortana, Google Assistant, iFlytek and Amazon Echo with an average SRoA of 52% and SNR of 9.65dB, shedding light on non-interactive physical attacks against voice control devices.

The population is aging, and becoming more tech-savvy. The United Nations predicts that by 2050, one in six people in the world will be over age 65 (up from one in 11 in 2019), and this increases to one in four in Europe and Northern America. Meanwhile, the proportion of American adults over 65 who own a smartphone has risen 24 percentage points from 2013-2017, and the majority have Internet in their homes. Smart devices and smart home technology have profound potential to transform how people age, their ability to live independently in later years, and their interactions with their circle of care. Cognitive health is a key component to independence and well-being in old age, and smart homes present many opportunities to measure cognitive status in a continuous, unobtrusive manner. In this article, we focus on speech as a measurement instrument for cognitive health. Existing methods of cognitive assessment suffer from a number of limitations that could be addressed through smart home speech sensing technologies. We begin with a brief tutorial on measuring cognitive status from speech, including some pointers to useful open-source software toolboxes for the interested reader. We then present an overview of the preliminary results from pilot studies on active and passive smart home speech sensing for the measurement of cognitive health, and conclude with some recommendations and challenge statements for the next wave of work in this area, to help overcome both technical and ethical barriers to success.

National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China, School of Artificial Intelligence, University of Chinese Academy of Sciences, China, and Peng Cheng Laboratory, China The cold-start recommendation is an urgent problem in contemporary online applications. It aims to provide users whose behaviors are literally sparse with as accurate recommendations as possible. Many data-driven algorithms, such as the widely used matrix factorization, underperform because of data sparseness. This work adopts the idea of meta-learning to solve the user's cold-start recommendation problem. We propose a meta-learning based cold-start sequential recommendation framework called metaCSR, including three main components: Diffusion Representer for learning better user/item embedding through information diffusion on the interaction graph; Sequential Recommender for capturing temporal dependencies of behavior sequences; Meta Learner for extracting and propagating transferable knowledge of prior users and learning a good initialization for new users. The extensive quantitative experiments on three widely-used datasets show the remarkable performance of metaCSR in dealing with user cold-start problem. Meanwhile, a series of qualitative analysis demonstrates that the proposed metaCSR has good generalization. Recommendation systems (RS) intend to address the information explosion by finding a set of items for users to meet their personalized interests in many online applications, such as E-commerce websites [17], social networks [14], video-sharing sites [3] and news websites [36]. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Abstracting with credit is permitted.

The ability to integrate multiple sources of information for business is revolutionized using Artificial Intelligence. Business strategy becomes a complex part due to the rise in competition. Using AI, we can perform certain tasks which fall beyond human efforts. A basic example of that is high-frequency stock trading. Let's look at particular areas of AI which help in revenue growth management.

I like puppies and soulcycle. Embeddings have pervaded the data scientist's toolkit, and dramatically changed how NLP, computer vision, and recommender systems work. However, many data scientists find them archaic and confusing. Many more use them blindly without understanding what they are. In this article, we'll deep dive into what embeddings are, how they work, and how they are often operationalized in real-world systems. To understand embeddings, we must first understand the basic requirements of a machine learning model. Specifically, most machine learning algorithms can only take low-dimensional numerical data as inputs. In the neural network below each of the input features must be numeric. That means that in domains such as recommender systems, we must transform non-numeric variables (ex.

Much has been published about conversational AI, and the bulk of it focuses on vertical chatbots, communication networks, industry patterns, and start-up opportunities (think Amazon Alexa, Apple Siri, Facebook M, Google Assistant, Microsoft Cortana). The capacity of AI to understand natural speech is still limited. The development of fully-automated, open-domain conversational assistants has therefore remained an open challenge. Nevertheless, the work shown below offers outstanding starting points for individuals. This is done for those people who wish to pursue the next step in AI communication.

Amid struggles to make headway in the smart speaker market, Apple has hired a new HomePod software head, according to Bloomberg's Mark Gurman. The company has reportedly brought onboard Afrooz Family, who co-founded the high-end audio startup Syng with former Apple designer Christopher Stringer. Apple's $349 HomePod arrived in 2018 to very mixed reviews, and was discontinued early this year. The company has noticeably failed to compete with smart speaker rivals, particularly Amazon's Alexa-powered Echo devices and Google's Assistant speaker family. Family worked for Apple between 2012 and 2016 and was on the original HomePod team before starting Syng.

Recommender systems attempt to identify and recommend the most preferable item (product-service) to individual users. These systems predict user interest in items based on related items, users, and the interactions between items and users. We aim to build an auto-routine and color scheme recommender system for home-based smart lighting that leverages a wealth of historical data and machine learning methods. We utilize an unsupervised method to recommend a routine for smart lighting. Moreover, by analyzing users’ daily logs, geographical location, temporal and usage information, we understand user preferences and predict their preferred light colors. To do so, users are clustered based on their geographical information and usage distribution. We then build and train a predictive model within each cluster and aggregate the results. Results indicate that models based on similar users increases the prediction accuracy, with and without prior knowledge about user preferences.

While music genre plays an enormous role in building and displaying social identity, the emotional expression of a song and -- even more importantly -- its emotional impression on the listener is often underestimated in the domain of music preferences. Only a few decades back, choosing music by genre and/or artist was effectively the only option. Want to hear live music? Well, choose an artist or a -- typically genre-based -- festival. Alright, check out our CD shelves categorized by genre and pick an album by an artist you like.

Welcome to Google Calendar: and help you if you are a virtual assistant I'll be your calendar coach! Learn everything you need to know about Google Calendar with this complete guide! Managing your own appointments and calendars can be daunting and stressful if you are working as a virtual assistant. Then you've come to the right place! Whether you are a complete beginner or just looking to refresh your existing knowledge of Google Calendar, this is the course for you.