Hamed Ketabdar

MagiTact: interaction with mobile devices based on compass (magnetic) sensor

In this work, we present a new technique for efficient use of 3D space around a mobile device for interaction with the device. Around Device Interaction (ADI) enables extending interaction space of small mobile and tangible devices beyond their physical boundary. Our proposed method is based on using compass (magnetic field) sensor integrated in mobile devices (e.g. iPhone 3GS, G1 Android). In this method, a properly shaped permanent magnet (e.g. in the shape of a rod, pen or a ring) is used for interaction. The user makes coarse gestures in the 3D space around the device using the magnet. Movement of the magnet affects the magnetic field sensed by the compass sensor integrated in the device. The temporal pattern of the gesture is then used as a basis for sending different interaction commands to the mobile device. Zooming, turning pages, accepting/rejecting calls, clicking items, controlling a music player, and game interaction are some example use cases. The proposed method does not impose changes in hardware specifications of the mobile device, and unlike optical methods is not limited by occlusion problems.

Enhanced Phone Posteriors for Improving Speech Recognition Systems

Using phone posterior probabilities has been increasingly explored for improving automatic speech recognition (ASR) systems. In this paper, we propose two approaches for hierarchically enhancing these phone posteriors, by integrating long acoustic context, as well as phonetic and lexical knowledge. In the first approach, phone posteriors estimated with a multilayer perceptron (MLP), are used as emission probabilities in hidden Markov model (HMM) forward-backward recursions. This yields new enhanced posterior estimates integrating HMM topological constraints (encoding specific phonetic and lexical knowledge), and context. In the second approach, temporal contexts of the regular MLP posteriors are postprocessed by a secondary MLP, in order to learn inter- and intra-dependencies between the phone posteriors. These dependencies are phonetic knowledge. The learned knowledge is integrated in the posterior estimation during the inference (forward pass) of the second MLP, resulting in enhanced phone posteriors. We investigate the use of the enhanced posteriors in hybrid HMM/artificial neural network (ANN) and Tandem configurations. We propose using the enhanced posteriors as replacement, or as complementary evidences to the regular MLP posteriors. The proposed methods have been tested on different small and large vocabulary databases, always resulting in consistent improvements in frame, phone, and word recognition rates.

Hierarchical integration of phonetic and lexical knowledge in phone posterior estimation

Phone posteriors has recently quite often used (as additional features or as local scores) to improve state-of-the-art automatic speech recognition (ASR) systems. Usually, better phone posterior estimates yield better ASR performance. In the present paper we present some initial, yet promising, work towards hierarchically improving these phone posteriors, by implicitly integrating phonetic and lexical knowledge. In the approach investigated here, phone posteriors estimated with a multilayer perceptron (MLP) and short (9 frames) temporal context, are used as input to a second MLP, spanning a longer temporal context (e.g. 19 frames of posteriors) and trained to refine the phone posterior estimates. The rationale behind this is that at the output of every MLP, the information stream is getting simpler (converging to a sequence of binary posterior vectors), and can thus be further processed (using a simpler classifier) by looking at a larger temporal window. Longer term dependencies can be interpreted as phonetic, sub-lexical and lexical knowledge. The resulting enhanced posteriors can then be used for phone and word recognition, in the same way as regular phone posteriors, in hybrid HMM/ANN or Tandem systems. The proposed method has been tested on TIMIT, OGI Numbers and Conversational Telephone Speech (CTS) databases, always resulting in consistent and significant improvements in both phone and word recognition rates.

MagiWrite: towards touchless digit entry using 3D space around mobile devices

In this work, we present a new approach for text (mainly digit) entry based on digit shaped gestures created in 3D space around a mobile device. Some new mobile devices such as Apple iPhone 3GS and Google Android are equipped with magnetic (compass) sensor. The main idea is to influence the magnetic sensor using a magnet taken in hand. The user draws (writes) digits in the 3D space around the device using the magnet taken in hand. Movement of the magnet changes temporal pattern of magnetic field around the device which is sensed and registered by the magnetic (compass) sensor. The registered pattern is then compared against already recorded templates for different digits. Such a text (digit) entry approach can be especially useful for small mobile devices in which it is hard to operate small buttons or touch screen. Using our technique, the text entry space extends beyond physical boundaries of the device. A demonstrator for this approach is implemented on Apple iPhone 3GS platform. It demonstrates registering a few templates for different digits, and recognizing digits written in the space around the device

Towards using embedded magnetic field sensor for around mobile device 3D interaction

We present a new technique based on using embedded compass (magnetic) sensor for efficient use of 3D space around a mobile device for interaction with the device. Around Device Interaction (ADI) enables extending interaction space of small mobile and tangible devices beyond their physical boundary. Our proposed method is based on using compass (magnetic field) sensor integrated in new mobile devices (e.g. iPhone 3GS, G1/2 Android). In this method, a properly shaped permanent magnet (e.g. a rod, pen or a ring) is used for interaction. The user makes coarse gestures in 3D space around the device using the magnet. Movement of the magnet affects magnetic field sensed by the compass sensor integrated in the device. The temporal pattern of the gesture is then used as a basis for sending different interaction commands to the mobile device. The proposed method does not impose changes in hardware and physical specifications of the mobile device, and unlike optical methods is not limited by occlusion problems. Therefore, it allows for efficient use of 3D space around device, including back of device. Zooming, turning pages, accepting/rejecting calls, clicking items, controlling a music player, and mobile game interaction are some example use cases. Initial evaluation of our algorithm using a prototype application developed for iPhone shows convincing gesture classification results.

System and methodology for using mobile phones in live remote monitoring of physical activities

In this paper, we propose a system and methodology for using mobile phones for monitoring physical activities of a user, and its applications in assisting elderly or people with need for special care and monitoring. The method is based on processing acceleration data provided by accelerometers integrated in new mobile phones. As the mobile phone is carried regularly by the user, the acceleration pattern can deliver information related to pattern of physical activities the user is engaged in. This information can be sent to a monitoring server, analyzed and presented as different health related factors for assistance, monitoring and healthcare purposes.

Assessing the vulnerability of magnetic gestural authentication to video-based shoulder surfing attacks

Secure user authentication on mobile phones is crucial, as they store highly sensitive information. Common approaches to authenticate a user on a mobile phone are based either on entering a PIN, a password, or drawing a pattern. However, these authentication methods are vulnerable to the shoulder surfing attack. The risk of this attack has increased since means for recording high-resolution videos are cheaply and widely accessible. If the attacker can videotape the authentication process, PINs, passwords, and patterns do not even provide the most basic level of security. In this project, we assessed the vulnerability of a magnetic gestural authentication method to the video-based shoulder surfing attack. We chose a scenario that is favourable to the attack-er. In a real world environment, we videotaped the interactions of four users performing magnetic signatures on a phone, in the presence of HD cameras from four different angles. We then recruited 22 participants and asked them to watch the videos and try to forge the signatures. The results revealed that with a certain threshold, i.e, th=1.67, none of the forging attacks was successful, whereas at this level all eligible login attempts were successfully recognized. The qualitative feedback also indicated that users found the magnetic gestural signature authentication method to be more secure than PIN-based and 2D signature methods.

MagiMusic: using embedded compass (magnetic) sensor for touch-less gesture based interaction with digital music instruments in mobile devices

Playing musical instruments such as chordophones, percussions and keyboard types accompany with harmonic interaction of players hand with the instruments. In this work, we present a novel approach that enables the user to imitate the music playing gestures around mobile devices. In our approach, touch-less gestures, which change magnetic field around the device, are employed for interaction. The activity of playing an instrument can be transparently pursued by moving a tiny magnet in hand around new generation of mobile phones equipped with embedded digital compass (magnetic sensor). The phonation intentions of the user can be simulated on the mobile device by capturing the gestural pattern using magnetic sensor. The proposed method allows digital imitation of a broad number of instruments while still being able to sense musical hits and relative plectrum gestures. It provides a framework for extending interaction space with music applications beyond physical boundaries of small mobile devices, and to 3D space around the device. This can allow for a more natural, comfortable and flexible interaction. We present several mobile music applications developed based on the proposed method for Apple iPhone 3GS.

Fall and emergency detection with mobile phones

In this demo, we present an application for mobile phones which can monitor physical activities of users and detect unexpected emergency situations such as a sudden fall or accident. Upon detection of such an event, the mobile phone can inform a designated center (by automatically calling or sending message) about the incident and its location. This can facilitate and speed up recovery and help process especially if the user is alone or the accident has happened in a deserted place. Such an application can be particularly useful for elderly people or people with physical and movement disabilities. The application operates based on analysis of user movements using data provided by accelerometers integrated in mobile phones.

Using More Informative Posterior Probabilities for Speech Recognition

In this paper, we present initial investigations towards boosting posterior probability based speech recognition systems by estimating more informative posteriors taking into account acoustic context (e.g., the whole utterance), as well as possible prior information (such as phonetic and lexical knowledge). These posteriors are estimated based on HMM state posterior probability definition (typically used in standard HMMs training). This approach provides a new, principled, theoretical framework for hierarchical estimation/use of more informative posteriors integrating appropriate context and prior knowledge. In the present work, we used the resulting posteriors as local scores for decoding. On the OGI numbers database, this resulted in significant performance improvement, compared to using MLP estimated posteriors for decoding (hybrid HMM/ANN approach) for clean and more specially for noisy speech. The system is also shown to be much less sensitive to tuning factors (such as phone deletion penalty, language model scaling) compared to the standard HMM/ANN and HMM/GMM systems, thus practically it does not need to be tuned to achieve the best possible performance