The retrieval of sounds in large databases can benefit from novel paradigms that exploit human-computer interaction. This work introduces the use of non-speech voice imitations as input queries in a large user-contributed sound repository. We address first the analysis of the human voice properties when imitating sounds. Second, we study the automatic classification of voice imitations in clust...

ii ACKNOWLEDGEMENTS A number of people have been involved in my work and I wish to express my warmest gratitude to everyone who supported and help me in different ways. First of all I am deeply grateful to my husband Jianlin Shi. Without his understanding, valuable advice and patience, my thesis could not have been attempted and completed. I want to express my heartfelt thanks to my supervisor ...

This paper presents a system for controlling audio mosaicing with a voice signal, which can be interpreted as a further step in voice-driven sound synthesis. Compared to voice-driven instrumental synthesis, it increases the variety in the synthesized timbre. Also, it provides a more direct interface for audio mosaicing applications, where the performer voice controls rhythmic, tonal and timbre ...

In this paper, we introduce a non-voice rejection method to perform Voice/Non-Voice (V/NV) classification using a fundamental frequency (F0) estimator called YIN. Although current speech recognition technology has achieved high performance, it is insufficient for some applications where high reliability is required, such as voice control of powered wheelchairs for disabled persons. The non-voic...

This work builds on the previous introduction [1] of a coupled experimental-computational system devised to fully characterize the thermal behavior of complex 3D submicron electronic devices. The new system replaces the laser-based surface temperature scanning approach with a CCD camera-based approach. As before, the thermo-reflectance thermography system is used to noninvasively measure with s...

Voice prosthesis-assisted speech rehabilitation after total laryngectomy has proven to be successful in the majority of patients and exceeds the results of traditional oesophageal speech. Nevertheless 10-30% failure rates are still reported. In part this is due to prosthesis-related problems, in particular ingrowth of Candida species in the valve-bearing parts of the devices. A new indwelling, ...

BACKGROUND The objective of this study was to determine if the design enhancements incorporated into the new Provox Vega Indwelling Voice prostheses result in any positive benefits in vivo. METHODS Using a randomized, crossover study design, 31 participants using tracheoesophageal speech postlaryngectomy completed a 3-week trial of the Provox Vega and a comparator device. Main outcome measure...

The paper presents the concept, implementation, and a feasibility study of a user interface technique, named VAVS (“voice-assisted visual search”). VAVS employs user’s voice input for assisting the user in searching for objects of interest in complex displays. User voice input is compared with attributes of visually presented objects and, if there is a match, the matching object is highlighted ...