Search

Automatic speech recognition (ASR) can be deployed in a previously unknown language, in less than 24 h, given just three resources: an acoustic model trained on other languages, a set of language-model training data, and a grapheme-to-phoneme (G2P) transducer to connect them. The LanguageNet G2Ps were created with the goal of being small, fast, and easy to port to a previously unseen language. Data come from pronunciation lexicons if available, but if there are no pronunciation lexicons in the target language, then data are generated from minimal resources: from a Wikipedia description of the target language, or from a one-hour interview with a native speaker of the language. Using such methods, the LanguageNet G2Ps now include simple models in nearly 150 languages, with trained finite state transducers in 122 languages, 59 of which are sufficiently well-resourced to permit measurement of their phone error rates. This paper proposes a measure of the distance between the G2Ps in different languages, and demonstrates that agglomerative clustering of the LanguageNet languages bears some resemblance to a phylogeographic language family tree. The LanguageNet G2Ps proposed in this paper have already been applied in three cross-language ASRs, using both hybrid and end-to-end neural architectures, and further experiments are ongoing.

Hydrocephalus is a common and costly neurological condition caused by the overproduction and/or impaired resorption of cerebrospinal fluid (CSF). The current standard of care, ventricular catheters (shunts), is prone to failure, which can result in nonspecific symptoms such as headaches, dizziness, and nausea. Current diagnostic tools for shunt failure such as computed tomography (CT), magnetic resonance imaging (MRI), radionuclide shunt patency studies (RSPSs), and ice pack–mediated thermodilution have disadvantages including high cost, poor accuracy, inconvenience, and safety concerns. Here, we developed and tested a noninvasive, skin-mounted, wearable measurement platform that incorporates arrays of thermal sensors and actuators for precise, continuous, or intermittent measurements of flow through subdermal shunts, without the drawbacks of other methods. Systematic theoretical and experimental benchtop studies demonstrate high performance across a range of practical operating conditions. Advanced electronics designs serve as the basis of a wireless embodiment for continuous monitoring based on rechargeable batteries and data transmission using Bluetooth protocols. Clinical studies involving five patients validate the sensor’s ability to detect the presence of CSF flow ( P = 0.012) and further distinguish between baseline flow, diminished flow, and distal shunt failure. Last, we demonstrate processing algorithms to translate measured data into quantitative flow rate. The sensor designs, fabrication schemes, wireless architectures, and patient trials reported here represent an advance in hydrocephalus diagnostics with ability to visualize flow in a simple, user-friendly mode, accessible to the physician and patient alike.

Browsing large audio archives is challenging because of the limitations of human audition and attention. However, this task becomes easier with a suitable visualization of the audio signal, such as a spectrogram transformed to make unusual audio events salient. This transformation maximizes the mutual information between an isolated event's spectrogram and an estimate of how salient the event appears in its surrounding context. When such spectrograms are computed and displayed with fluid zooming over many temporal orders of magnitude, sparse events in long audio recordings can be detected more quickly and more easily. In particular, in a 1/10-real-time acoustic event detection task, subjects who were shown saliency-maximized rather than conventional spectrograms performed significantly better. Saliency maximization also improves the mutual information between the ground truth of nonbackground sounds and visual saliency, more than other common enhancements to visualization.

Stable pH is an established biomarker of health, relevant to all tissues of the body, including the heart. Clinical monitoring of pH in a practical manner, with high spatiotemporal resolution, is particularly difficult in organs such as the heart due to its soft mechanics, curvilinear geometry, heterogeneous surfaces, and continuous, complex rhythmic motion. The results presented here illustrate that advanced strategies in materials assembly and electrochemical growth can yield interconnected arrays of miniaturized IrOx pH sensors encapsulated in thin, low-modulus elastomers to yield conformal monitoring systems capable of noninvasive measurements on the surface of the beating heart. A thirty channel custom data acquisition system enables spatiotemporal pH mapping with a single potentiostat. In vitro testing reveals super-Nernstian sensitivity with excellent uniformity (69.9 ± 2.2 mV/pH), linear response to temperature (-1.6 mV °C(-1) ), and minimal influence of extracellular ions (

We have built a virtual-reality simulator to design quadrotor robots that increase the independence of elderly persons living alone. The simulator lets us measure under what conditions a robot makes someone feel intrigued, or alarmed, or unconcerned, extending to nonhumanoids the studies of emotion that have been done for robots with facial expressions. This better model of how the virtual robot is perceived lets us agilely improve its appearance and behavior, containing the combinatorial explosion of parameters to study in costlier real-world experiments. The residence and the robot are rendered with Unity, and viewed with an Oculus Rift. Audio corresponding to flight maneuvers is resynthesized from recordings of an actual quadrotor. Flight dynamics using L1 adaptive control run in MATLAB and Simulink. Through menus operated by a Leap Motion hand tracker, the human subject commands the quadrotor to fly to various rooms (Unity waypoints), along precomputed paths that avoid collisions. The flight path is varied through a mathematical mapping to Laban Motion Factors (e.g., directness, sustainedness, lightness, and boundness) to provoke a range of responses. The subject's emotion is estimated from heart rate, skin conductance, and head tilt from the Rift's IMU (which is a quick metric for discomfort level).

Distributed scene graphs are important in virtual reality, both in collaborative virtual environments and in cluster rendering. Modern scalable visualization systems have high local throughput, but collaborative virtual environments (VEs) over a wide-area network (WAN) share data at much lower rates. This complicates the use of one scene graph across the whole application. Myriad is an extension of the Syzygy VR toolkit in which individual scene graphs form a peer-to-peer network. Myriad connections filter scene graph updates and create flexible relationships between nodes of the scene graph. Myriad's sharing is fine-grained: the properties of individual scene graph nodes to share are dynamically specified (in C++ or Python). Myriad permits transient inconsistency, relaxing resource requirements in collaborative VEs. A test application, WorldWideCrowd, demonstrates collaborative prototyping of a 300-avatar crowd animation viewed on two PC-cluster displays and edited on low-powered laptops, desktops, and over a WAN. We have further used our framework to facilitate collaborative educational experiences and as a vehicle for undergraduates to experiment with shared virtual worlds. Copyright © 2006 John Wiley & Sons, Ltd.

Software-based musical instruments have controls for input, a sound synthesizer for output, and mappings connecting the two. An effective layout of controls considers how many degrees of freedom each has, as well as the overhead of selecting each one while performing. An isolated mapping from one control to one synthesis parameter needs an appropriate choice of proportional, integral or derivative control (the control's value, or that value's rate of change, drives the synthesis parameter's value, or that value's rate of change). Beyond this, a compound mapping cross-coupling several controls and synthesis parameters can surprisingly increase the performer's intuitive understanding of the instrument.

Sitting down to write this soon after it ended, and still dizzy from eleven concerts and many paper sessions in just six days, I will try to give a taste and synopsis of what I think was most interesting, amusing, challenging, or even inspiring at the 1998 International Computer Music Conference (ICMC). But it won't be easy. First, an overview: ICMC '98 was held at the University of Michigan in Ann Arbor, a quintessential American college town, one of the biggest and best of its breed-meaning that cafes and brew pubs abound, yet, come Friday night, it is still nearly impossible to find one with space to take you and your party of 30 ICMC-ers. But we did manage upon a few occasions. In such a welter of presentations, it is possible to bring out only the highlights, but one can also note trends as perceived by the reviewer, who has been going to these conferences since 1984. Some of the newest technologies have to do with the World Wide Web, and particularly with the Web-oriented programming language Java, as might have been predicted from observing the computer scene outside of music. Much of the work here might be described as belonging to the comparatively uninteresting category of software ports. Still, the impact of Web-based accessibility may bring new benefits by reaching new audiences, composers, and performers, and perhaps by facilitating greater communication and interchange within an expanding community, the latter being just why Conseil Europ6en pour la Recherche Nucl~aire (CERN) developed the Web in the first place. In this context, I would mention some of the Java-based programs that are springing up. Among these are synthesis programs (Phil Burk's Jsyn for real-time synthesis, and of course, IRCAM's latest FTS "front end," jMAX-more on this later), and some intriguing developments in notation programs. Thanks to the ubiquity and cross-platform aspects of Java, notation programs seem to be at a threshold for unifying tools across many platforms and many user communities, something that has been notably lacking until now. Of these efforts, the Web-based approach taken by Kai Renz and Holger Hoos in their Salieri program, which builds on Guido, appears extremely promising. It will be particularly interesting once the Java implementation they are working on is completed. Another important development is the arrival en masse of cheap hardware/software systems that can synthesize and process sounds on the fly. These are represented in such works as MSP and jMax, but also in a number of others. For ex

We describe a collaboration between mathematicians interested in visualizing curved three-dimensional spaces and researchers building next-generation virtual-reality environments such as ALICE, a six-sided, rigid-walled virtual-reality chamber. This environment integrates active-stereo imaging, wireless motion-tracking and wireless-headphone sound. To reduce cost, the display is driven by a cluster of commodity computers instead of a traditional graphics supercomputer. The mathematical application tested in this environment is an implementation of Thurston’s eight-fold way; these eight three-dimensional geometries are conjectured to suffice for describing all possible three-dimensional manifolds or universes.

cote interne IRCAM: Bargar00a; None / None; National audience; Coney Island

We are developing the audio display for a CAVE‐type virtual reality theater, a 3‐m cube with displays covering all six rigid faces. The user’s headgear continuously reports ear positions so headphones would be possible, but we nevertheless prefer loudspeakers because this enhances the sense of total immersion. Because sounds produced at the loudspeakers are distorted by the room impulse responses, we therefore face the problem of controlling the sound at the listener’s two ears. Our proposed solution consists of open‐loop acoustic point control, i.e., dereverberation. The room impulse responses from each loudspeaker to each ear of the listener are inverted using multichannel inversion methods, to create exactly the desired sound field at the listener’s ears. Because the actual room impulse responses cannot be measured in real time (as the listener walks around), instead the impulse responses simulated by the image‐source method is used. A new evaluation criterion is proposed to quantitatively evaluate both the simulation and the open‐loop dereverberation. The actual impulse responses used for this evaluation are measured with a starter pistol, since this best approximates the point source assumed by the image‐source method.

Non‐speech audio event detection (AED) could be used for low‐cost, spatially diffuse surveillance applications, e.g., monitoring of vehicle activity in a national park, or of footsteps in a hallway. Experiments have shown that non‐speech AED benefits from the dynamic inference strategies such as the hidden Markov model (HMM), but that the acoustic features useful for non‐speech events may not be the same as those useful for speech. One possible solution is a tandem HMM: an HMM whose observation vector is constructed from the output of an instantaneous discriminative classifier, e.g., a neural network. The use of tandem HMMs for non‐speech AED is hindered, however, by the relatively small size of most non‐speech‐audio training corpora. This talk will demonstrate that tandem HMMs can be trained to detect non‐speech audio events using a novel form of regularized training: Baum–Welch back‐propagation (as proposed by Bengio et al.), using the conjugate‐gradient adaptive form of the Baum–Welch auxiliary functio...