Voice Queries Research Articles

Replies to Queries in Gynecologic Oncology by Bard, Bing and the Google Assistant

When women receive a diagnosis of a gynecologic malignancy, they can have questions about their diagnosis or treatment that can result in voice queries to virtual assistants for more information. Recent advancement in artificial intelligence (AI) has transformed the landscape of medical information accessibility. The Google virtual assistant (VA) outperformed Siri, Alexa and Cortana in voice queries presented prior to the explosive implementation of AI in early 2023. The efforts presented here focus on determining if advances in AI in the last 12 months have improved the accuracy of Google VA responses related to gynecologic oncology. Previous questions were utilized to form a common basis for queries prior to 2023 and responses in 2024. Correct answers were obtained from the UpToDate medical resource. Responses related to gynecologic oncology were obtained using Google VA, as well as the generative AI chatbots Google Bard/Gemini and Microsoft Bing-Copilot. The AI narrative responses varied in length and positioning of answers within the response. Google Bard/Gemini achieved an 87.5% accuracy rate, while Microsoft Bing-Copilot reached 83.3%. In contrast, the Google VA’s accuracy in audible responses improved from 18% prior to 2023 to 63% in 2024. While the accuracy of the Google VA has improved in the last year, it underperformed Google Bard/Gemini and Microsoft Bing-Copilot so there is considerable room for further improved accuracy.

Exploring the impact of SEO-based ranking factors for voice queries through machine learning

The use of voice search is proliferating and expected to grow into the foreseeable future; this is why websites increasingly optimize their content associated with voice-based search to improve their ranking. In this era of rapid growth in voice search technology, it is a topical matter that needs research. Moreover, many predictions about its future excite the subject and require systematic investigation. This research aims to analyze important features that contribute to the SEO of webpages. Therefore, there is a need to examine various ranking factors that improve the ranking of the webpages for voice search queries on the Search Engine Results Page (SERP). This study consists of two phases. The first phase comprises systematic data acquisition and identifying important SEO-based ranking factors. The second phase includes a longitudinal case study to evaluate the impact and significance of identified factors. To achieve this goal, we conduct experiments on methodical combinations of features through machine learning algorithms such as Support Vector Machine, Logistic Regression, Naive Bayes Classifier, K-Nearest Neighbors, Decision Trees and Random Forest. Comparing results for multiple feature designs evaluates the contributing nature of specific features in SEO-based optimization for ranking. Results suggest the importance of the newly identified feature set (FF) outperforms baselines (EF and EFN) by a significant margin. A longitudinal case study on a blog over four months confirms that optimizing these features improves page ranking; therefore, webmasters must optimize these features while preparing the webpage.

Holographic voice-interactive system with Taylor Rayleigh-Sommerfeld based point cloud gridding

In recent years, intelligent voice interaction technology and holographic display technology have garnered significant attention. We propose a holographic voice-interactive system. The holographic voice interaction system can provide users with a virtual assistant proficient in accurately handling user voice queries, facilitating smoother interactions. Additionally, users can interact with virtual objects via holographic projection, enhancing realism and engagement. In this research, we introduce the U-blocks and U-net based reverse attention residual algorithm to generate more effective and accurate point cloud datasets during the acquisition phase. Furthermore, we integrate the ChatGLM pre-trained language model as the core module for voice interaction in the holographic display system, covering aspects such as text interaction and output control. Additionally, we propose a Taylor Rayleigh-Sommerfeld point cloud gridding method aimed at improving the computational speed of hologram generation. We validate the feasibility of our proposed methods through numerical simulations and optical experiments.

Streamlining Industrial Robot Maintenance: An Intelligent Voice Query Approach for Enhanced Efficiency

Streamlining Industrial Robot Maintenance: An Intelligent Voice Query Approach for Enhanced Efficiency

Evaluation of Replies to Voice Queries in Gynecologic Oncology by Virtual Assistants Siri, Alexa, Google, and Cortana

Women that receive news that they have a malignancy of gynecologic origin can have questions about their diagnosis. These questions might be posed as voice queries to the virtual assistants Siri, Alexa, Google, and Cortana. Because our world has increasingly adopted smart phones and standalone voice query devices, this study focused on the accuracy of audible replies by the virtual assistants (VAs) Siri, Alexa, Google, and Cortana to voice queries related to gynecologic oncology. Twenty-one evaluators analyzed VA audible answers to select voice queries related to gynecologic oncology. Questions were posed in three different ways for each voice query in order to maximize the likelihood of acceptability to the VAs in a 24-question panel. For general queries that were not related to gynecologic oncology, Google provided the most correct audible replies (83.3% correct), followed by Alexa (66.7% correct), Siri (45.8% correct), and Cortana (20.8% correct). For gynecologic oncology-related queries, the accuracy of the VAs was considerably lower: Google provided the most correct audible replies (18.1%), followed by Alexa (6.5%), Siri (5.5%), and Cortana (2.3%). There was a considerable drop in the accuracy of audible replies to oral queries on topics in gynecologic oncology relative to general queries that were not related to gynecologic oncology. There is considerable room for improvement in VA performance, so that caution is advised when using VAs for medical queries in gynecologic oncology. Our specific findings related to gynecologic oncology extend the work of others with regard to the low usability of general medical information obtained from VAs, so that reliance on conversational assistants for actionable medical information represents a safety risk for patients and consumers.

Application of persuasive systems design principles to design a self-management application user interface for Hispanic informal dementia caregivers: user preferences and perceptions.

ObjectiveWe designed an mHealth application (app) user interface (UI) prototype informed by participatory design sessions, persuasive systems design (PSD) principles, and Lorig and Holman’s self-management behavior framework to support self-management activities of Hispanic informal dementia caregivers and assessed their perceptions and preferences regarding features and functions of the app.Materials and MethodsOur observational usability study design employed qualitative methods and forced choice preference assessments to identify: (1) the relationship between user preferences for UI features and functions and PSD principles and (2) user preferences for UI design features and functions and app functionality. We evaluated 16 pairs of mHealth app UI prototype designs. Eight paper-based paired designs were used to assess the relationship between PSD principles and caregiver preferences for UI features and functions to support self-management. An Apple iPad WIFI 32GB was used to display another 8 paired designs and assess caregiver preferences for UI functions to support the self-management process.ResultsCaregivers preferred an app UI with features and functions that incorporated a greater number of PSD principles and included an infographic to facilitate self-management. Moreover, caregivers preferred a design that did not depend on manual data entry, opting instead for functions such as drop-down list, drag-and-drop, and voice query to prioritize, choose, decide, and search when performing self-management activities.ConclusionOur assessment approaches allowed us to discern which UI features, functions, and designs caregivers preferred. The targeted application of PSD principles in UI designs holds promise for supporting personalized problem identification, goal setting, decision-making, and action planning as strategies for improving caregiver self-management confidence.

Grow Kisan: E-Agriculture App

Abstract: Web apps and services facilitate information, communication, entertainment, and leisure. Web apps have ushered in a new era. In India, information and communication technology (ICT) in agriculture is a relatively new subject aimed at increasing agricultural and rural output. It entails the development of novel ICT-based rural applications. Farmers can benefit from ICT innovation by receiving timely and accurate information and services, resulting in a more productive agricultural climate.This study offers a web-based tool for farmers that will help them with their agricultural tasks while also keeping them informed about new government programmes. “Grow Kisan” is a service that gives agriculture-related information to Indian farmers in rural areas who face financial and connectivity challenges. The concept makes use of existing government services and mobile services to deliver a solution to the current situation with the least amount of cost to the farmer. The application system provides customers with all of the information that is relevant for their own land, searches, on-line crop management, statistic profit summaries, a statistical summary of their land by cultivating a specific crop, and the FAO recommendation not to use water, but to use fertilisation to increase productivity; "Fertilization" With GPS and Web methods, the system allows effective land management, monitoring, and data supply. The device's interface is more "image-based" than "word based," whereby even analphabets will comprehend and utilise it. The initiative focuses largely on small landowners, who truly may do miracles if specific instructions are supplied for effective land management and knowledge on the crops most appropriate for their territory. Not only will the initiative offer the smallholder with a free callback service, but also some films and soundtracks to show how things are to be accomplished in the country. The most essential component is video conferencing since farmers may ask through video and demonstrate whether they have a problem with crops and soil. For example, how to apply a certain herbicide and how to seed the soil for improved production, etc. A mobile cloud service for responding to Tomato Diseases is a voice-based response technique (VBAT) that is designed for farmers to receive voice queries in their natural language utilising the keyboard for the use of mic or text inquiries. Via speech and text the user will get the appropriate responses. India's cellular subscribers are 900 million. Keywords: E-Agriculture, Crop information, E-commerce, weather prediction, Agro - assistant.

Robust voice querying with MUVE

Recently proposed voice query interfaces translate voice input into SQL queries. Unreliable speech recognition on top of the intrinsic challenges of text-to-SQL translation makes it hard to reliably interpret user input. We present MUVE (Multiplots for Voice quEries), a system for robust voice querying. MUVE reduces the impact of ambiguous voice queries by filling the screen with multiplots, capturing results of phonetically similar queries. It maps voice input to a probability distribution over query candidates, executes a selected subset of queries, and visualizes their results in a multiplot. Our goal is to maximize probability to show the correct query result. Also, we want to optimize the visualization (e.g., by coloring a subset of likely results) in order to minimize expected time until users find the correct result. Via a user study, we validate a simple cost model estimating the latter overhead. The resulting optimization problem is NP-hard. We propose an exhaustive algorithm, based on integer programming, as well as a greedy heuristic. As shown in a corresponding user study, MUVE enables users to identify accurate results faster, compared to prior work.

Exploiting peer-to-peer communications for query privacy preservation in voice assistant systems.

Voice assistant system (VAS) is a popular technology for users to interact with the Internet and the Internet-of-Things devices. In the VAS, voice queries are linked to users' accounts, resulting in long-term and continuous profiling at the service provider. In this paper, we propose a VAS anonymizer aiming to mix the queries of the VAS users to increase the source anonymity. The VAS anonymizer is equipped with a pattern-matching scheme, which allows VAS devices to find effective peer relays without disclosing their query patterns. Furthermore, the VAS anonymizer is equipped with anonymity evaluation modules for evaluating real-time single query, thus reducing the risk of pattern violation at the relays. Both the requester and the relay will evaluate the real-time query based on the resulting anonymity. Only if the anonymity evaluations at both requester and relay are positive, the query will be sent to the service provider via the relay. The VAS anonymizers at VAS devices coordinate the query uploading such that the sources of the queries are anonymized, and the service provider is unable to link the voice queries to individual users. In the experiments using our customized VAS devices and the Amazon Cloud servers, the computation and communication overhead of the matching scheme is shown to be efficient, and the anonymity evaluation modules are shown to be effective in protecting the privacy of the requesters and the relays.

Conversational replies to oral queries in gynecologic oncology by Google, Alexa and Siri

Objective: Voice queries to virtual assistant platforms on Google, Apple, and Amazon can retrieve information. This study focused on the accuracy of audible information in gynecologic oncology retrieved by each platform.

Multi-user searchable encryption voice in home IoT system

With the development of home IoT voice systems that can provide interfaces, such as Amazon Alex, it is easy to disclose personal privacy when people search voice conveniently. It becomes a challenge how to search voice effectively with privacy-preserving for multi-user. In the paper, we propose a multi-user searchable encrypted voice scheme (MUSEV). The outline is as the follows. voices are divided into two parts. One is answer. The other is query, or key words of voices. Answer part will be encrypted and query part will be converted into features. The feature and encrypted answer are bound together and uploaded to the server. If the feature is matched successfully, the answer part encrypted can be acquired. First, the feature of voice query is extracted using Mel Frequency Cepstral Coefficents (MFCC). Next, the feature of voice query and voice answer encrypted by Advanced Encryption Standard (AES) are bound. Before uploading the server, we adopt obfuscation function to hide the features on the server. The features obfuscated will be matched. If the query feature is matched successfully, the encrypted voice answer associated with it will be returned to a user. Then, the user can get the plaintext of voice answer by decrypting these voice answers encrypted. To improve multi-user retrieval performance, we employ Long Short-Term Memory networks (LSTM) for voice conversion between users. Meantime, Diffie-Hellman algorithm is used to exchange parameters between users to enhance security. Theoretical analysis and experimental results prove that MUSEV is secure and effective.

Design a Chatbot for Chennai Corporation Using Logistic Regression Algorithm

Chatbots are the famous nowadays in business because of its service offered to the community at large. They provide support of 24*7 for business in terms of customercare, helpline, planning, analyzing and decision making. In this paper, a chatbot for Chennai corporation is proposed. This chatbot helps the citizens in providing the responses for their queries related to civic problems. There is no such system is available to handle the public grievances automatically. This system handles the public query and the relevant suggestion and responses will be given promptly. The chatbot receives the text or voice input and processed. The voice recognition module used to recognize the voice query and the voice to text convertor used to convert the voice data into text format. The matchmaking process used to match the input query with the available data set and the relevant responses is generated. If no match is for the query, the matchmaker will find the relevant response from online sources. The output channel equipped with the text to voice converter which converts the text data into voice and it will be delivered to the end user. The naïve bayers and logistic regression algorithm is implemented for classifying the query and the performance is compared. The result shows that the logistic regression algorithm outperform well with the precision and recall values.

Evaluating the quality of voice assistants’ responses to consumer health questions about vaccines: an exploratory comparison of Alexa, Google Assistant and Siri

ObjectiveTo assess the quality and accuracy of the voice assistants (VAs), Amazon Alexa, Siri and Google Assistant, in answering consumer health questions about vaccine safety and use.MethodsResponses of each VA...

03:45 PM Abstract No. 38 The development of a machine learning smart speaker application for device sizing in interventional radiology

Smart speakers such as the Amazon Echo and Google Home offer a fundamentally new method for interacting with software. These tools offer unique value in interventional radiology (IR), as a conversational voice interface allows IR physicians to interact with software and retrieve information without breaking sterile scrub. We present a smart speaker application developed specifically for use during IR procedures, using natural language processing (NLP) and machine learning to rapidly provide information about device sizing and compatibility in IR. We have developed a device sizing application for the Google Home smart speaker device. This application processes a human voice query and provides sizing recommendations. It can, for example, specify the minimum sheath size needed for a particular Amplatzer plug, among many other sizing tasks. Size data was acquired in an extensive literature review, with data compiled for 475 IR devices (catheters, sheaths, stents, vascular plugs, etc.). Natural language processing was implemented using Dialogflow, which extracted information of interest from an input query. Logic operations and other data processing were performed using a Python script deployed to the cloud. The conversational application is found to offer an effective tool for device sizing in interventional radiology, achieving excellent performance for a wide range of tasks. Technically satisfactory outcomes were seen using a training data set of 10 samples for each information category and a classification threshold of 0.3. Smart speakers have the potential to offer immense value in interventional radiology, giving proceduralists the ability to access modern information technology while maintaining procedural sterility. This work represents an early step in developing a suite of smart speaker IR tools for intra-procedural support. Future applications may focus on sterile approaches to querying the inventory database, performing dictations during procedural downtime, and accessing key data from the electronic medical record. These tools offer significant value to interventional radiologists and allow us to benefit from the power of machine learning.

From textual orality to oral textuality: The case of voice queries

This study analyzes the phenomenon of digital voice search queries against the background of the fluid and changing balance in the orality–literacy osmosis of different historical eras. In attempting to theoretically conceptualize the unique oral characteristics of this new digital feature, this article argues that as the result of technological considerations, voice querying manifests an attempt to discipline oral words – to pronounce them while thinking of their written form. The article also considers the oxymoron of ‘looking up’ information through spoken words; the effect of an interface that stresses the use of the oral words as an event; the devocalization of queries, as they transform into a written form; and the implications of browsing the Internet through oral word searches, especially for young children. It concludes that the integration of these oral features can be explained by the affordances of digital media on the one hand and the ‘revival’ of intuitive preprint features attempting to ease the cognitive demands of print culture on the other hand.

Research on voice search behavior in the last 10 years

ABSTRACTVoice search enables users to issue spoken information requests and retrieve desired information on web/mobile search interfaces. We conducted a literature review to examine the extent to which existing studies have addressed voice search behavior, with a focus on the employed methodologies and the focused topics in these studies. Fourteen relevant studies conducted since 2008 were identified from four publication databases. These studies were mainly focused on three aspects of search behavior: voice query characteristics, reformulation strategies, and users' perception/satisfaction. Our results provide a snapshot of how users perform and perceive voice search in order to inform future research and design of voice search systems.

The Characteristics of Voice Search

The growing popularity of mobile search and the advancement in voice recognition technologies have opened the door for web search users to speak their queries rather than type them. While this kind of voice search is still in its infancy, it is gradually becoming more widespread. In this article, we report a comprehensive voice search query log analysis of a commercial web search engine’s mobile application. We compare voice and text search by various aspects, with special focus on the semantic and syntactic characteristics of the queries. Our analysis suggests that voice queries focus more on audio-visual content and question answering and less on social networking and adult domains. In addition, voice queries are more commonly submitted on the go. We also conduct an empirical evaluation showing that the language of voice queries is closer to natural language than the language of text queries. Our analysis points out further differences between voice and text search. We discuss the implications of these differences for the design of future voice-enabled web search tools.

Poe in Cyberspace: The “Mobile-Friendly” Sites

Poe in Cyberspace: The “Mobile-Friendly” Sites

NLU Framework for Voice Enabling Non-Native Applications on Smart Devices

Voice is a critical user interface on smart devices (wearables, phones, speakers, televisions) to access applications (or services) available on them. Unfortunately, only a few native applications (provided by the OS developer) are typically voice enabled in devices of today. Since, the utility of a smart device is determined more by the strength of external applications developed for the device, voice enabling non-native applications in a scalable, seamless manner within the device is a critical use case and is the focus of our work. We have developed a Natural Language Understanding (NLU) framework that uses templates supported by the application (as determined by the application developer). This framework can be employed in any mobile OS (Android, iOS, Tizen, Android wear) for a wide range of devices. To aid this demonstration, we have implemented the framework as a service in Android OS. When the user issues a voice command, the natural language query is obtained by this service (using one of local, cloud based or hybrid speech recognizers). The service then executes our NLU framework to identify the relevant application and particular action details. In this demonstration, we will showcase this NLU framework implemented as an Android service on a set of applications that will be installed on the fly. Specifically, we will show how the voice queries are understood and necessary services are launched on android smart wearables and phones.

Speaker Identification using SVM during Oriya Speech Recognition

In this research paper, we have developed a system that identifies users by their voices and helped them to retrieve the information using their voice queries. The system takes into account speaker identification as well as speech recognition i.e. two pattern recognition techniques in speech domain. The conglomeration of speaker identification task and speech recognition task provides multitude of facilities in comparison to isolated approach. The speaker identification task is achieved by using SVM where as speech recognition is based on HMM. We have used two different types of corpora for training the system. Gamma tone cepstral coefficients and mel frequency cepstral coefficients are extracted for speaker identification and speech recognition respectively. The accuracy of the system is measured from two perspective i.e. accuracy of speaker identity and accuracy of speech recognition task. The accuracy of the speaker identification is enhanced by adopting the speech recognition at the initial stage of speaker identification.