Recommender systems are software applications that help users to find items of interest in situations of information overload. Current research often assumes a one-shot interaction paradigm, where ...the users’ preferences are estimated based on past observed behavior and where the presentation of a ranked list of suggestions is the main, one-directional form of user interaction. Conversational recommender systems (CRS) take a different approach and support a richer set of interactions. These interactions can, for example, help to improve the preference elicitation process or allow the user to ask questions about the recommendations and to give feedback. The interest in CRS has significantly increased in the past few years. This development is mainly due to the significant progress in the area of natural language processing, the emergence of new voice-controlled home assistants, and the increased use of chatbot technology. With this article, we provide a detailed survey of existing approaches to conversational recommendation. We categorize these approaches in various dimensions, e.g., in terms of the supported user intents or the knowledge they use in the background. Moreover, we discuss technological approaches, review how CRS are evaluated, and finally identify a number of gaps that deserve more research in the future.
Underwater communication is a critical and challenging issue, on account of the complex underwater environment. This study introduces an underwater wireless communication approach via Maxwell's ...displacement current generated by a triboelectric nanogenerator. Underwater electric field can be generated through a wire connected to a triboelectric nanogenerator, while current signal can be inducted in an underwater receiver certain distance away. The received current signals are basically immune to disturbances from salinity, turbidity and submerged obstacles. Even after passing through a 100 m long spiral water pipe, the electric signals are not distorted in waveform. By modulating and demodulating the current signals generated by a sound driven triboelectric nanogenerator, texts and images can be transmitted in a water tank at 16 bits/s. An underwater lighting system is operated by the triboelectric nanogenerator-based voice-activated controller wirelessly. This triboelectric nanogenerator-based approach can form the basis for an alternative wireless communication in complex underwater environments.
Artificial Intelligent (AI) In-home Voice Assistants have seen unprecedented growth. However, we have little understanding on the factors motivating individuals to use such devices. Given the unique ...characteristics of the technology, in the main hands free, controlled by voice, and the presentation of a voice user interface, the current technology adoption models are not comprehensive enough to explain the adoption of this new technology. Focusing on voice interactions, this research combines the theoretical foundations of U> with technology theories to gain a clearer understanding on the motivations for adopting and using in-home voice assistants. This research presents a conceptual model on the use of voice controlled technology and an empirical validation of the model through the use of Structural Equation Modelling with a sample of 724 in-home voice assistant users. The findings illustrate that individuals are motivated by the (1) utilitarian benefits, (2) symbolic benefits and (3) social benefits provided by voice assistants, the results found that hedonic benefits only motivate the use of in-home voice assistants in smaller households. Additionally, the research establishes a moderating role of perceived privacy risks in dampening and negatively influencing the use of in-home voice assistants.
•Use of AI in-home voice assistants is driven by utilitarian & symbolic benefits.•Social benefits (attractiveness & presence) motivate VA use.•Hedonic benefits have no influence on motivating VA use.•Perceived privacy risks has a dampening and negative effect on VA use.•Household size influences the benefits motivating VA use.
Soliciting and incorporating employee voice is essential to organizational performance, yet some managers display a strong aversion to improvement-oriented input from subordinates. To help to explain ...this maladaptive tendency, we tested the hypothesis that managers with low managerial self-efficacy (that is, low perceived ability to meet the elevated competence expectations associated with managerial roles) seek to minimize voice as a way of compensating for a threatened ego. The results of two studies support this idea. In a field study (Study 1), managers with low managerial self-efficacy were less likely than others to solicit input, leading to lower levels of employee voice. A follow-up experimental study (Study 2) showed that: (a) manipulating low managerial self-efficacy led to voice aversion (that is, decreased voice solicitation, negative evaluations of an employee who spoke up, and reduced implementation of voice); and (b) the observed voice aversion associated with low managerial self-efficacy was driven by ego defensiveness. We discuss the theoretical and practical implications of these findings, as well as highlight directions for future research on voice, management, and leadership.
The present study demonstrates how three psychological antecedents (psychological safety, felt obligation for constructive change, and organization-based self-esteem) uniquely, differentially, and ...interactively predict supervisory reports of promotive and prohibitive "voice" behavior. Using a two-wave panel design, we collected data from a sample of 239 employees to examine the hypothesized relationships. Our results showed that felt obligation was most strongly related to subsequent promotive voice; psychological safety was most strongly related to subsequent prohibitive voice; and organization-based self-esteem was reciprocally related to promotive voice. Further, although felt obligation strengthened the positive effect of psychological safety on both forms of voice, organization-based self-esteem weakened this effect for promotive voice. Theoretical and practical implications are discussed.
This article examines whether managerial responses to employees speaking up depend on the type of voice exhibited—that is, whether employees speak up in challenging or supportive ways. In one field ...study and two experimental studies, I found that managers view employees who engage in more challenging forms of voice as worse performers and endorse their ideas less than those who engage in supportive forms of voice. Further, perceptions of loyalty and threat mediated these relationships, but in different ways. I discuss implications for research on voice, proactivity, and social persuasion.
This article reports a keyword-spotting (KWS) chip for voice-controlled devices. It features a number of techniques to enhance the performance, area, and power efficiencies: 1) a fast-sampling ...convolutional neural network (FS-CNN) that eliminates the power-hungry feature extractors and reduces the decision latency; 2) an always-retention 5T-SRAM that features word-voltage switches to reduce the leakage power and single bitline (BL) operation to halve the SRAM read power compared to the typical 6T-SRAM; and 3) a high-resolution sparsity-aware computing (HR-SAC) unit that enhances the precision and output swing of the multiply–accumulate (MAC) computation. Benchmarking with the state-of-the-art, our KWS chip prototyped in 28-nm CMOS scores a Formula Omitted90% accuracy for the 11-class Google speech command dataset (GSCD) at 2.91 Formula Omitted, which corresponds to a 2.91-nJ energy/decision. The achieved latency is 2 ms/decision, and the core area is 0.05 Formula Omitted, including the full KWS model.
Voice interface has been a dominant User Interface (UI) channel in the popular smart home environment. Although Voice Control System (VCS) brings users conveniences, it is extremely vulnerable to ...spoofing attacks (e.g., hidden/inaudible command attack) due to its broadcast nature. In this study, to thwart spoofing attacks, we propose WSVA, a device-free voice liveness detection system based on the prevalent wireless signals generated by IoT devices without requiring user to carry any additional sensor or device. The basic insight of WSVA to distinguish the authentic voice command from a spoofed one is checking the consistency between the voice signal and its corresponding mouth motions, which can be captured by wireless signals. To achieve this goal, WSVA builds a theoretical model to describe the correlations among the wireless signal changes, the mouth motions, and the syllables in the voice command. Then, WSVA selects appropriate features from both voice and wireless signals, and calculates the consistency between these two types of signals to determine whether the VCS is suffering from the spoofing attack. To demonstrate the feasibility of WSVA, we conduct a case study on Samsung SmartThings platform and include WSVA as a new application, which is expected to significantly enhance the security of the existing VCS. We evaluate WSVA with various voice commands in different scenarios. Experimental results demonstrate that WSVA achieves the overall 99 percent true accept rate with 1 percent false accept rate with a good scalability and low latency.
PDF
