Toshiharu Horiuchi

A pointing system based on acoustic position estimation and gravity sensing

This paper presents a novel pointing system for distant displays based on an acoustic position estimation technique in conjunction with a gravity sensor on a smartphone. The system is designed to interact with a distant large display such as a television set at home or digital signage in public. The system consists of a display, two loudspeakers set around the display, and a smartphone as a pointing device containing a microphone and a gravity sensor inside. The position of the pointer is theoretically determined by the position and direction of the smartphone, given by the three-dimensional acoustic position estimation. This smartphone-based system approximates the position and direction by the two-dimensional position of the microphone horizontally and the pitch angle from the gravity sensor vertically. The loudspeakers of the prototype system radiate burst signals of 20 kHz modulated by pre-windowed M-sequence, which are reproducible by normal television sets. The position of the smartphone is estimated at a frame rate of 23 Hz, and the pointer is rendered at a frame rate of over 100 Hz with linear interpolation and with a latency of 0.4 second.

CLOSE/DISTANT TALKER DISCRIMINATION BASED ON KURTOSIS OF LINEAR PREDICTION RESIDUAL SIGNALS

Desired/undesired speech discrimination is as important as speech/non-speech discrimination to achieve useful applications such as speech interfaces and teleconferencing systems. Conventional methods of voice activity detection (VAD) utilize the directional information of sound sources to distinguish desired from undesired speech. However, these methods have to utilize multiple microphones to estimate the directions of sound sources. Here, we propose a new method to discriminate desired from undesired speech with a single microphone. We assumed that the desired talkers would be close to the microphone, and the proposed method could distinguish close/distant-talking speech from observed signals based on the kurtosis of the linear prediction (LP) residual signals. The experimental results revealed that the proposed method could distinguish close-talking speech from distant-talking speech within a 10% equal error rate (EER) in ordinary reverberant environments with less processing time.

Typing Tutor: Individualized Tutoring in Text Entry for Older Adults Based on Input Stumble Detection

Many older adults are interested in smartphones. However most of them encounter difficulties in self-instruction and need support. Text entry, which is essential for various applications, is one of the most difficult operations to master. In this paper, we propose Typing Tutor, an individualized tutoring system for text entry that detects input stumbles and provides instructions. By conducting two user studies, we clarify the common difficulties that novice older adults experience and how skill level is related to input stumbles. Based on these studies, we develop Typing Tutor to support learning how to enter text on a smartphone. A two-week evaluation experiment with novice older adults (65+) showed that Typing Tutor was effective in improving their text entry proficiency, especially in the initial stage of use.

Interactive music video application for smartphones based on free-viewpoint video and audio rendering

This paper presents a novel interactive music video application for smartphones based on free-viewpoint video technology in conjunction with three-dimensional positional audio technology. A user can enjoy a music video from a moving viewpoint that the user can manipulate by the touch screen, with the positional audio through the headphone. A user can even manipulate the positions of the performers on the stage as well as the viewpoint. The application, consisting of our audio rendering engine for multiple AAC ADTS files and our video rendering engine for multiple H.264 ES files, runs on a smartphone in stand-alone mode. The application has been released as official content from a music label for Android and iOS.

Acoustic-based passive pointing system for distant screens

This paper presents a passive pointing system for a distant screen based on an acoustic position estimation technology in conjunction with a gravity sensor on a smartphone. The system is designed to interact with a distant large screen such as a television set at home or digital signage in public. The system consists of a screen, two loudspeakers set around the screen, and a smartphone as a pointing device having a microphone and a gravity sensor inside. The position of the pointer is theoretically determined by the position and direction. This smartphone-based system approximates the position and direction by the two-dimensional position of the microphone horizontally and the pitch angle from the gravity sensor vertically. In this paper, we report experiments to evaluate the performance of the system. The loudspeakers of the system radiate burst signal from 18 to 24 kHz. The position of the smartphone is estimated at a frame rate of 15 Hz with a latency of 0.4 second. The accuracy of the pointer was measured as an angle error below 10 degrees for 100% of all frames. We confirmed that it has enough accuracy to point to each region which is divided area in the screen for applications such as quiz or questionnaire on digital signage.

Typing Tutor: Individualized Tutoring in Text Entry for Older Adults Based on Statistical Input Stumble Detection

Many older adults are interested in smartphones. However, most of them encounter difficulties in selfinstruction and need support. Text entry, which is essential for various applications, is one of the most difficult operations to master. In this paper, we propose Typing Tutor, an individualized tutoring system for text entry that detects input stumbles using a statistical approach and provides instructions. By conducting two user studies, we clarify the common difficulties that novice older adults experience and how skill level is related to input stumbles with a 12-key layout for Japanese. Based on the study, we develop Typing Tutor to support learning how to enter text on a smartphone. A two-week evaluation experiment with novice older adults (65+) showed that Typing Tutor was effective in improving their text entry proficiency, especially in the initial stage of use. In addition, we demonstrate the applicability of Typing Tutor to other keyboards and languages with the QWERTY layout for Japanese and English.

Assistive Typing Application for Older Adults Based on Input Stumble Detection

Smartphones offer new opportunities to improve the lives of older adults. Although many older adults are interested in smartphones, most of them face difficulties in self-instruction and need support. Text entry, which is essential for various applications, is one of the most difficult operations to master. Therefore, we propose an assistive typing application that detects input stumbles and provides instructions for typing presented sentences, instead of having human tutors help older adults resolve the input stumbles by themselves. First, we investigated the ways that novice older adults have problems with text entry on smartphones. Next, we confirmed the acceptability of being provided with instructions for text entry by Wizard-of-Oz (WoZ). Then, we constructed an assistive typing application based on the collected data from two user studies. An evaluation with novice older adults (60+) showed that the assistive typing application increased typing speed by 17.2% and reduced input stumble incidence by 59.1% compared with the users’ initial performance. Improvement rates were almost the same as those achieved with human tutors.

Measurement of acoustic transmission properties of a handset with a piezoelectric vibrator using a head and torso simulator

This paper clarifies the difference between the acoustic transmission properties of the pinna simulator and a real pinna by a subjective assessment of the sound produced by vibration of the handset with a piezoelectric vibrator using a head and torso simulator (HATS). Recently, a piezoelectric vibrator that vibrates a pinna to produce and transmit sounds was adopted as a receiver on cell-phones and smartphones to improve perceived sound quality in noisy environments. The HATS, used for handset testing in accordance with ITU-T recommendations, has a silicone-rubber pinna simulator to realistically reproduce natural acoustic properties with its human-like shape and stiffness. However, the handset with the piezoelectric vibrator is beyond the scope and was not tested on the HATS. In this paper, we conducted a subjective assessment test that adjusted the gain of pure tones through the pinna simulator to make them auditorily equal to those through the real pinna. We used the HATS, B&K Type 4128-D. The results ...