Voice Navigation Research Articles

Should voice navigation prompts be earlier and more complicated? A study of drivers’ visual attention, physiology and operating performance

Voice navigation systems can help drivers access information about road conditions and make correct decisions, but inappropriate information level and information prompt timing may lead to untimely processing of information, distraction, or even misjudgment of drivers, which in turn may cause safety hazards. The purpose of this study is to investigate the effects of voice information level and information prompt timing on drivers’ driving behavior and physiological characteristics. Twenty-seven participants were recruited to conduct driving simulator experiments. The results showed that the driver’s visual attention is more focused and the driving performance is better when the voice navigation prompts contain four information units (driving directions, traffic facility information, distance information, and road condition information at the same time). Moreover, when the voice navigation prompts with four information units were played 300 meters from the intersection, the driver’s overall driving performance was the highest. The results offer additional theoretical insights for the design of voice navigation systems, aiding drivers in accurately understanding driving conditions and providing them with ample reaction time to enhance their driving decisions.

A Review on Voice Navigation System for the Visually Impaired

A ground-breaking voice navigation system seems as a ray of light in a world where blind people must overcome enormous obstacles to navigate strange places. For those with vision impairments, safely and independently navigating in unfamiliar situations presents substantial obstacles. This system is a paradigm shift in providing safe and independent mobility assistance for the visually handicapped, as it makes use of cutting-edge technologies. The voice navigation system gives users the confidence to confidently navigate uncharted territory by seamlessly integrating computer vision and machine learning capabilities. With the use of real-time obstacle classification and recognition capabilities, the system can give users vital information about their surroundings, empowering them to make wise decisions while traveling. The system's smartphone-based platform, which provides an intuitive interface that can be accessed with voice commands, is its basis. By utilizing deep learning algorithms and pre-trained models, the system can precisely identify barriers and guide people across intricate environments. Precise positioning and route planning are made possible by the system's integration of GPS technology. Users receive up-to-date information on their location and the most efficient route to their destination via voice-activated instructions and advice. Individual user preferences are catered to by customizable options, which guarantee a tailored and user-friendly experience. A wider user base can utilize the system, democratizing access to necessary navigation tools, due to its affordability and interoperability with commonly available smartphone devices. The results of experimental tests highlight the effectiveness of the system, showing that it can reliably and accurately guide visually impaired people across a variety of surroundings. Through the promotion of increased autonomy and mobility, the voice navigation system enables users to move with unprecedented liberty and self-assurance, surmounting obstacles and opening up novel prospects. Key Words: : Voice navigation system, Machine learning, GPS technology, Deep learning algorithms, Navigation tools.

Exploring the Role of Artificial Intelligence in the Design Industry: Client Satisfaction through Enhancing Quality while Preserving Human Creativity

The integration of artificial intelligence (AI) is driving significant transformations within the design industry. As AI technologies advance, they are increasingly being incorporated at various stages of the design process, from conceptualization to final product delivery. This incorporation holds the potential to revolutionize the industry by enhancing efficiency, quality, and client satisfaction, while simultaneously preserving human innovation. The influence of AI is evident in its ability to streamline processes and optimize workflows, thereby reducing the time and effort necessary to complete projects. This leads to quicker turnaround times and lower costs, ultimately improving client satisfaction. Additionally, AI-driven personalization enables designers to create tailored solutions by analyzing user data and preferences, fostering a stronger connection between designers and clients. AI also promotes inclusivity and accessibility by offering solutions that cater to users with diverse abilities, such as AI-powered voice navigation tools for the visually impaired. However, concerns persist regarding the potential erosion of human creativity, with some fearing that AI could lead to homogenized and impersonal designs. To address these concerns, scholars advocate for “human-AI collaboration,” wherein AI augments rather than replaces human creativity, thereby enabling designers to explore new creative possibilities. As AI adoption continues to expand, it is essential to ensure that ethical AI practices are upheld, emphasizing transparency, accountability, and the elimination of bias. By prioritizing these principles and embracing a collaborative approach, the design industry can fully harness AI’s potential while maintaining the indispensable human element. This equilibrium will enable the industry to deliver innovative and high-quality designs that meet the needs of a diverse clientele.

PC Voice Navigation using Python

With the use of a software programmer called PC Voice Navigation System, users may navigate and operate their laptops and desktops by speaking instructions. The development of a PC voice navigation system utilizing the Python programming language is covered in this research report. An intuitive and hands-free user experience is offered by the system thanks to the utilization of text-to-voice synthesis, natural language [1]. processing, and speech recognition. A personal assistant for Linux-based systems is what it seeks to create. Cortana for Windows and Siri for iOS are two examples of virtual assistants that inspire Jarvis. It's been built to offer a User-Friendly Interface (UFI) for carrying out a range of operations by using certain Well-Defined Commands. Either voice commands or

Sparse Bayesian Least-Mean-Squares Algorithm

Echo seriously damages the speech communication quality of vehicle communication system and seriously interferes with the normal operation of voice navigation, voice dialing, and other functions of the vehicle-mounted human-machine interaction platform. This brief proposes a sparse Bayesian least-mean-squares (SBLMS) algorithm which is designed to exploit the sparseness of echo channel for improving the quality of echo cancellation. The proposed SBLMS algorithm is derived by performing Bayesian inference in an equivalent linear Gaussian observation model with diagonal proportionate matrix. To avoid algorithmic performance degradation at steady-state, a step-size lower bound is derived for the proposed SBLMS algorithm. Also, a reset parameter method is designed to improve the tracking performance of the proposed SBLMS algorithm in a sudden change scenario. Finally, the good performance of the proposed SBLMS algorithm is confirmed by system identification and acoustic echo cancellation.

Design and implementation of a secure mobile phone-based route navigator (mGuide), adapted for the visually challenged people

This paper is focused on the development of a turn-by-turn voice navigation mobile application “mGuide” adapted for visually challenged people (VCP). The application was developed in response to the challenges of outdoor navigation by VCP. The application optimizes five map servers to give not only the best real-time routing at any instance but also faster loading and retrieval of route data into the phone’s storage. The destination points of the user are obtained in real time using open street maps and stored in the database. Once the destination has been set and mode of travel chosen, the software gives turn-by-turn voice navigation till the destination is reached. In addition, the application can be able to read inbox messages as they are received. Furthermore, the application gives an audio alert to the user in case of lost route and redirects the user using alternative route. Testing of the application was done using 9 totally blind students and 1 partially blind student from Kenyatta University in Kenya, who were successfully guided. In testing the performance of the whole system, no sound alerts between 0 and 10 m from the middle of the road were heard. However, as the user deviated more than the 10 m from the path, sound alerts are heard. In conclusion, sound alert due to wrong turn is averagely 5.23 s.

Recognizing speech in voice messages

The level of development of information technology makes it possible to use speech recognition technologies in a wide range of human life and activities. It is very convenient to use the voice interface: voice search for the necessary documents, dialing a phone number, managing IOT devices, voice navigation, simple text dictation. Since the natural language interface provides an additional convenience for a person when typing, sending voice messages has become common among users. In this case, voice messages are audio files. But it is not always available and convenient for the recipient to listen to such messages. This problem can be solved with the help of an automatic speech recognition system (ASR). The article describes the stages and elements of the process of processing and recognition of natural language by audio signal. Modern technologies of automatic speech recognition and problems with choosing among them are indicated. Modern automatic speech recognition (ASR) systems understand fully spontaneous speech that is natural, not memorized, contains signs of stuttering or even minor errors. At the same time, they are still too expensive to develop from scratch. So companies are faced with a choice between using the cloud API for ASR developed by the tech giants and using open source solutions. The analysis of the latest research and publications on the processing of voice data is considered. A software solution for automatic conversion of voice messages into text is proposed. The interface to the voice signal delivery system is proposed to be made as a chat bot in the messenger. The article presents the main components of the system, the algorithm of the chat bot, modern technologies for the development, implementation and configuration of the chat bot in the messenger

Speech Audio Modeling by Means of Causal Moving Average Equipped Gated Attention

In the paper we compare different attention mechanisms on the task of audio generation using unsupervised approaches following previous work in language modeling. It is important problem, as far as speech synthesis technology could be used to convert textual information into acoustic waveform signals. These representations can be conveniently integrated into mobile devices and used in such applications as voice messengers or email apps. Sometimes it is difficult to understand and read important messages when being abroad. The lack of appropriate computer systems or some security problems may arise. With this technology, e-mail messages can be listened quickly and efficiently on smartphones, boosting productivity. Apart from that, it is used to assist visually impaired people, so that, for instance, the screen content can be automatically read aloud to a blind user. Nowadays, home appliances, like slow cookers can use this system too for reading culinary recipes, automobiles for voice navigation to the destination spot, or language learners for pronunciation teaching. Speech generation is the opposite problem of automatic speech recognition (ASR) and is researched since the second half of the eighteen's century. Also, this technology also helps vocally handicapped people find a way to communicate with others who do not understand sign language. However, there is a problem, related to the fact that the audio sampling rate is very high, thus leading to very long sequences which are computationally difficult to model. Second challenge is that speech signals with the same semantic meaning can be represented by a lot of signals with significant variability, which is caused by channel environment, pronunciation or speaker timbre characteristics. To overcome these problems, we train an autoencoder model to discretize continuous audio signal into a finite set of discriminative audio tokens which have a lower sampling rate. Subsequently, autoregressive models, which are not conditioned on text, are trained on this representation space to predict the next token, based on previous sequence elements. Hence, this modeling approach resembles causal language modeling. In our study, we show that unlike in the original MEGA work, traditional attention outperforms moving average equipped gated attention, which shows that EMA gated attention is not stable yet and requires careful hyper-parameter optimization.

Influence of smartphone traffic application information on drivers’ route choice behaviours

The active traffic management system disseminates traffic information to drivers to guide their route choice, so as to alleviate traffic congestion. Most drivers are highly dependent on mobile navigation APP, and the display form of mobile navigation information is of great importance. In order to improve drivers’ compliance with guidance information, this research accommodates for information that disseminate time attribute (when to provide the traffic information) and display format attribute (voice navigation or not, flat map or three-dimensional [3D] map) and also explores the interaction effects between individual and trip characteristics. A revealed preference (RP) and stated preference (SP) survey consisting of 831 respondents is conducted in Nanjing, China. Then three kinds of panel logit model are established to fit the survey data. According to the model results, it is found that drivers with aggressive style are more sensitive to travel time, and drivers who are familiar with the road network are more sensitive to the 3D map with voice navigation format. The results of parameter estimation are also used for the trade-off analysis of various exogenous variables. The findings of this study provide useful insights for the development of mobile navigation APPs, personalized path recommendation and congestion pricing strategies.

Self‐Powered Intelligent Voice Navigation Tactile Pavement Based on High‐Output Hybrid Nanogenerator

AbstractImproving the safety and usability of the blind movement is of great significance. The blind navigation system has always been the focus of attention. However, achieving an unconscious interaction and long‐term operation with high navigation accuracy is an urgent challenge. In this study, a distributed self‐powered intelligent voice navigation tactile pavement (SVP) based on a hybrid nanogenerator for blind navigation is reported. More than 4‐s effective output time is achieved under a single instantaneous pressure to the hybrid nanogenerator. The system is integrated with an inertial storage hybrid nanogenerator (ISNG), RF transmitter module, and voice broadcast module. It has the advantages of outstanding navigation accuracy, fatigue resistance (16 000 cycles), temperature stability (−50 to 50 °C), no required operation, and easy fabrication. The SVP may solve the difficulties of GPS navigation delay and lack of map information and realize the accurate identification and feedback of key locations, providing an effective and unconscious interaction navigation strategy for the blind. Integrating the hybrid nanogenerator under the road can provide an energy supply for the construction of the Internet of Things and smart city in the future.

Voice Navigation Created by VIP Improves Spatial Performance in People with Impaired Vision.

The difficulty associated with spatial navigation is one of the main obstacles to independent living for visually impaired people. With a lack of visual feedback, visually impaired people must identify information from the external environment through other sense organs. This study employed an observational survey to assess voice navigation version A, created by visually impaired people, and voice navigation version B, created by non-visually impaired people. Thirty-two simulated visually impaired people were assigned to conduct task assessments of voice navigation version A and version B. For mission 1, the mean completion rate is 0.988 ± 0.049 (version A); the mean error rate is 0.125 ± 0.182 (version A). For mission 2, the mean completion rate is 0.953 ± 0.148 (version A); the mean error rate is 0.094 ± 0.198 (version A). The assessment results concluded that version A has a higher completion rate (p = 0.001) and a lower error rate (p = 0.001). In the assessment of subjective satisfaction, all the indicators regarding the impression of navigation directives in version A were significantly superior to those indicators in version B. It appears that version A has a different logic of framing than version B. In future applications, a voice navigation version shall be built, according to the way visually impaired people think, because it will facilitate the direction guide when there is a lack of visual feedback.

Optimization method of navigation information mode under the condition of multi-exit city expressway

In recent years, mobile phone navigation software has been widely used, but the voice broadcast information of many navigation software is not clear, which is easy to cause confused driving. Urban expressway is an important artery of the city. The road and traffic conditions of urban expressways are extremely complicated, and there are many types of exits, which can easily cause confused driving. Therefore, optimization of navigation modes under the condition of multi-exit urban expressways is particularly important. Based on the experimental data of simulated driving, this paper focuses on the influence of voice navigation broadcast timing on driving under urban expressway, founding driver’s behavior is significantly different under diverse navigation modes. This paper uses the principal component analysis method to comprehensively evaluate the navigation broadcast timing, and gives the optimal navigation broadcast timings for various multi-exit urban expressways. In most cases, the first broadcast time should be 1500m from the exit. This paper clarifies the impact of navigation broadcast timing on driving, and optimizes the navigation mode of multi-exit urban expressways, which is of great significance for reducing yaw under navigation and improving navigation services.

PFHTS-IDSS: A Hybrid HTS-based Framework for Indonesian Speech Synthesis via Phoneme and Full-context Lab

In recent years, globalization has highlighted the importance of having machines that can truly provide customized communication for different languages. Majority of the research in the field focus on developing technologies for widely used languages such as English. In this study, we apply HMM-based speech synthesis (HTS) technology for Indonesian language. The proposed hybrid HTS-based framework, PFHTS-IDSS, uses phoneme and full-context lab to synthesize Indonesian with higher accuracy. First, we identify a list of Indonesian phonemes according to the initial-final structure of Chinese language. Based on this, we add zero-initials that match the Indonesian acoustic performance and HTS, which can make the synthesized speech natural and smooth. Second, we consider Indonesian phonemes as synthetic units to synthesize speech through the triphone and full-context lab. In addition, we design context properties of the full-context lab and the corresponding question set to train the acoustic model, which can eliminate machine sounds. Experimental results suggest that the accuracy of phoneme segmentation (PSA) and the naturalness of speech synthesis (SSN) are significantly improved via PFHTS-IDSS. Especially, the PSA of selecting phonemes as synthetic units reaches 88.3% and the corresponding SSN based on full-context lab is 4.1. The results demonstrated by PFHTS-IDSS presented in this paper may be used in multilingual free interactive system to promote better communication in terms of voice navigation, intelligent speaker and question-answering system.

North in the head: spatial reference frame and map orientation

North in the head: spatial reference frame and map orientation

A Structure Design of Virtual and Real Fusion Intelligent Equipment and Multimodal Navigational Interaction Algorithm

Virtual experiments have become an interesting research topic in the field of education. However, we found that there are some limitations in the current virtual experiments: first, the researchers used the virtual effects of the simulation to represent the virtual experiments, which led to decrease the immersion of the user's simulated experiments; second, most of the virtual experiments are only mouse or touch screen interactive mode, which reduces the realism of user simulation experiments; third, students independently explore the experimental operation process and spend too much time simulating the experiment, which leads to problems such as overloading the operation and low interaction efficiency. In order to solve the above problems, we propose and implement a multimodal navigational interaction virtual and real fusion chemistry laboratory (MNIVRFCL). We design a new sensing structure intelligent equipment and propose a multimodal navigational interaction algorithm (MMNI) based on auditory and tactile channel, which are verified and applied in MNIVRFCL. The MMNI algorithm can detect user's specific behaviors to understand their behavioral intentions, and then the system guide and rectify users' current correct or incorrect behaviors in the form of voice navigation broadcasts. Finally, we achieve the purpose that students can use virtual and real fusion interactions through tactile and auditory channels, they can independently complete simulations and learning experiments based on experimental navigation. The experimental statistic results show that system's successful understanding of intention is 91.48%, and prove the MNIVRFCL operational load reduce by 23.81% compared to the pure virtual experiment, it can reduce the time consumption and improves the students' interaction efficiency.

METHOD OF LOCATION IDENTEFICATION BY VOICE NAVIGATION IN THE INDOOR SYSTEMS

The article deals with tasks of indoor navigation with the usage of voice comands. To solvetasks of indoor navigation there are used different approaches, such as mapping the premises, determining the current position, determining the trajectory. With the rapid improvements in software and hardware, last years it's become more popular to use voice assistance. The implementation of voice navigation and speech recognition is a very complicated, time consuming and costly process. Usually existing on the market speech recognition systems are not properly documented, described, without possibility to integrate it with other software, limited in number of requests available for users, or paid. To formulate the requirements to suchsystems authors analyzed functionality of the most widely used voice assistants such as Google Assistant, Siri, Cortana. For indoor navigation systems existing solutions provide voice assistance for navigation within previously defined route. In the paper authors propose a method of determining a predetermined indoor location based on received voice commands, which uses fuzzy output to determine the position of the beacon according to the voice command. For voice recognition there were used hidden Markovs models. The developed method is used in BLE 4.0 based navigation systems and unlike existing ones, it allows user to use voice commands and fuzzy rules to find a specific location. Developed method was implemented in the Smart-Campus Mobile Application by developing the module of voice navigation, which enhances the ability to interact with the university's infrastructure and make it more inclusive for visitors, students and staff.

Effects of In-vehicle Information on Driver Blink Characteristics and Workload

A real-vehicle experiment was carried out to study the effects of in-vehicle information on driver workload, during which data of the driver blink duration and frequency were collected to check for discrepancies among drivers with and without vehicle navigation usage. In the meanwhile, the blink characteristics of drivers with vehicle navigation device mounted at three different positions were explored through image prompt or image & sound multi-channel simultaneous prompt. Experimental results showed that when the data of blink with a duration of 0-200ms was distributed at a 10ms interval, the driver blink count distribution curve shows obvious bimodal characteristics. The peak of blink with 50-60ms duration was lower than that with 10-20ms duration when vehicle navigation was not used, and higher when vehicle navigation was used. The difference between medium and long blinks was not significant when the navigation device was mounted at different positions, yet the short blinks showed a significant difference. The peaks of blink count without voice navigation were all greater than those with voice navigation. In particular, without voice navigation, the short blinks increased obviously, and the medium blinks increased relatively, but the long blinks remained almost unchanged. The above results indicate that the driver workload was greater when using vehicle navigation. When the navigation device is installed in position B, the driver workload reaches the minimum. Using voice navigation could reduce driver workload.

Analysis of Psychological Influences on Navigation Use While Driving Based on Extended Theory of Planned Behavior

As GPS navigation systems become more powerful, they offer the convenience of more efficient travel, and the use of such navigational aids while driving is now prevalent. Numerous issues still exist during actual use, however, such as incomprehensibility and inaccuracy of voice navigation prompts. The majority of studies have focused on humanized design and the influence on driving behavior of GPS navigation systems, while the psychological factors underlying drivers’ decisions to use them have received little attention. This study employs the extended theory of planned behavior (TPB) to investigate the psychological factors that influence drivers’ use of GPS navigation systems, including the additional variables of navigation involvement, navigation information quality, and distraction perception. Independent t-tests revealed that female, non-professional, novice, and highly educated drivers were more likely to use navigation systems. Factors analysis proved the extended TPB questionnaire to be valid and reliable. Structural equation modeling showed that attitude (0.19), subjective norms (0.14), perceived behavioral control (0.29), navigation involvement (0.36), and information quality (0.16) significantly influenced drivers’ intentions on the use of navigation. However, distraction perception (–0.05) had no significant influence. These findings demonstrate the need for navigation systems which serve drivers better. For navigation system manufacturers, the humanized design should be strengthened. For highway transportation agencies, more consistent designs for road signs are needed to improve the cooperativity between navigation and traffic signs.

GPS based Voice Navigation System for Blind People

GPS based Voice Navigation System for Blind People

Computer Vision for Vulnerable Road Users using Machine Learning

Transportation has become a very important component for all ages in today’s life. However, seniors often find difficulty in travelling by public transport or even by their own vehicles. Thus, they are considered as Vulnerable Road Users (VRUs). This research mainly concentrates on creating an application that helps the elderly mobile users in virtually screening of directions using GPS, tracking of sidewalks, identifying the traffic signals and other sign boards. MATLAB/Simulink serves as the main software used in developing this application. Images and other types of data are captured using sensors on Android devices. Then MATLAB is used to perform deep learning. Transfer learning is another machine learning technique where a model like AlexNet developed for one task is retrained to perform a second task. In this research, AlexNet is used to identify and classify different traffic warning signs in real-time. A detailed description of this method and the results are presented in this paper. Once the MATLAB-based program is developed, it can be converted into Java codes when needed. Using Android Studio, the code can be used in the application. VRUs with mobility impairments and vision deficiencies often find it difficult to use wheelchair on sidewalks. This paper also presents a sidewalk tracking system with a departure warning. In this research, Hough Transform is used to present the detection of sidewalk. This sidewalk tracking system can provide the user with essential information that can minimize the risk of an accident. This system can identify and track the present sidewalks. Any unintended departure towards the edge of sidewalks will be detected and notified to the user. Elaborated implementation of this system and results are presented in this paper. Re-routing the user when they approach the end of the sidewalk is left for future work. The application will further be developed to provide a voice navigation informing the departure warning, a traffic signal or a recognized sign board.