The Experts below are selected from a list of 57954 Experts worldwide ranked by ideXlab platform
Gilles Boulianne - One of the best experts on this subject based on the ideXlab platform.
-
language independent voice passphrase verification
International Conference on Acoustics Speech and Signal Processing, 2015Co-Authors: Gilles BoulianneAbstract:Voice passphrase verification is the task of deciding whether an Audio Recording contains a given passphrase. It is usually done by evaluating the likelihood of the passphrase reference text given the Audio, which requires a different ASR system for each language. Here we look at verification when the passphrase reference is an Audio Recording instead of a text. We propose a decision likelihood ratio derived from a generative model. Training is unsupervised and needs only Audio, without labelling, so the method applies to any language for which recorded Audio exists. We report experiments on English and Urdu telephone speech, and show that our model-based likelihood ratio largely outperforms a baseline of DTW based on MFCC feature vectors.
-
ICASSP - Language-independent voice passphrase verification
2015 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2015Co-Authors: Gilles BoulianneAbstract:Voice passphrase verification is the task of deciding whether an Audio Recording contains a given passphrase. It is usually done by evaluating the likelihood of the passphrase reference text given the Audio, which requires a different ASR system for each language. Here we look at verification when the passphrase reference is an Audio Recording instead of a text. We propose a decision likelihood ratio derived from a generative model. Training is unsupervised and needs only Audio, without labelling, so the method applies to any language for which recorded Audio exists. We report experiments on English and Urdu telephone speech, and show that our model-based likelihood ratio largely outperforms a baseline of DTW based on MFCC feature vectors.
Huseyin Hacihabiboglu - One of the best experts on this subject based on the ideXlab platform.
-
Perceptual Soundfield Reconstruction in Three Dimensions via Sound Field Extrapolation
ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2019Co-Authors: Ege Erdem, Enzo De Sena, Huseyin Hacihabiboglu, Zoran CvetkovićAbstract:Perceptual sound field reconstruction (PSR) is a spatial Audio Recording and reproduction method based on the application of stereophonic panning laws in microphone array design. PSR allows rendering a perceptually veridical and stable auditory perspective in the horizontal plane of the listener, and involves Recording using near-coincident microphone arrays. This paper extends the PSR concept to three dimensions using sound field extrapolation carried out in the spherical-harmonic domain. Sound field rendering is performed using a two-level loudspeaker rig. An active-intensity-based analysis of the rendered sound field shows that the proposed approach can render direction of monochromatic plane waves accurately.
-
perceptual spatial Audio Recording simulation and rendering an overview of spatial Audio techniques based on psychoacoustics
IEEE Signal Processing Magazine, 2017Co-Authors: Huseyin Hacihabiboglu, Enzo De Sena, Zoran Cvetkovic, James Johnston, Julius O SmithAbstract:Developments in immersive Audio technologies have been evolving in two directions: physically motivated systems and perceptually motivated systems. Physically motivated techniques aim to reproduce a physically accurate approximation of desired sound fields by employing a very high equipment load and sophisticated, computationally intensive algorithms. Perceptually motivated techniques, however, aim to render only the perceptually relevant aspects of the sound scene by means of modest computational and equipment load. This article presents an overview of perceptually motivated techniques, with a focus on multichannel Audio Recording and reproduction, Audio source and reflection culling, and artificial reverberators.
Enzo De Sena - One of the best experts on this subject based on the ideXlab platform.
-
Perceptual Soundfield Reconstruction in Three Dimensions via Sound Field Extrapolation
ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2019Co-Authors: Ege Erdem, Enzo De Sena, Huseyin Hacihabiboglu, Zoran CvetkovićAbstract:Perceptual sound field reconstruction (PSR) is a spatial Audio Recording and reproduction method based on the application of stereophonic panning laws in microphone array design. PSR allows rendering a perceptually veridical and stable auditory perspective in the horizontal plane of the listener, and involves Recording using near-coincident microphone arrays. This paper extends the PSR concept to three dimensions using sound field extrapolation carried out in the spherical-harmonic domain. Sound field rendering is performed using a two-level loudspeaker rig. An active-intensity-based analysis of the rendered sound field shows that the proposed approach can render direction of monochromatic plane waves accurately.
-
perceptual spatial Audio Recording simulation and rendering an overview of spatial Audio techniques based on psychoacoustics
IEEE Signal Processing Magazine, 2017Co-Authors: Huseyin Hacihabiboglu, Enzo De Sena, Zoran Cvetkovic, James Johnston, Julius O SmithAbstract:Developments in immersive Audio technologies have been evolving in two directions: physically motivated systems and perceptually motivated systems. Physically motivated techniques aim to reproduce a physically accurate approximation of desired sound fields by employing a very high equipment load and sophisticated, computationally intensive algorithms. Perceptually motivated techniques, however, aim to render only the perceptually relevant aspects of the sound scene by means of modest computational and equipment load. This article presents an overview of perceptually motivated techniques, with a focus on multichannel Audio Recording and reproduction, Audio source and reflection culling, and artificial reverberators.
Robert W. Grotke - One of the best experts on this subject based on the ideXlab platform.
-
Techniques for Audio Recording Vocalizations of Tropical Birds
Ornithological Monographs, 1997Co-Authors: Gregory F. Budney, Robert W. GrotkeAbstract:Audio Recordings of tropical birds are important tools for biologists involved in the study, management, and conservation of birdlife; the ability to acoustically identify a species in a number of tropical habitats is essential. Recording method, equipment, and the condition of equipment can affect the accuracy and quantity of Audio Recordings collected. Suitability of currently available analog Recording systems, emerging digital Recording formats, and differing microphone designs for field work varies. This paper discusses essential and effective criteria that can be used to select a Recording system based upon research goals and financial resources. To survey and study tropical birds, biologists increasingly recognize that it is essential to be able to identify the birds by their sounds and to have the skill to make Audio Recordings of their voices (Parker 1991). Although several papers have been written on making Audio Recordings of bird sounds for research (Gulledge 1976; Wickstrom 1982; Ranft 1991; Vielliard 1993), recent advances in Recording technology, together with the specific requirements of the tropical researcher, warrant revisiting and updating the information presented in these publications. This paper presents the fundamental technical information required to master the operation of a field Recording system and prepares the recordist for situations that may be encountered in the tropics. Resumen. Las grabaciones del sonido de aves tropicales son herramientas importantes para los biologos envueltos en el estudio, manejo y conservacion de las aves. La habilidad para identificar acusticamente a una especie en varios tipos de habitats tropicales es esencial. El metodo de grabacion, equipo y la condicion del equipo, pueden afectar la exactitud y cantidad de grabaciones coleccionadas. La conveniencia de los sistemas de grabacion analogos disponibles al presente, los formatos de grabaciones digitales actuales y los diferentes disenos de microfonos para trabajo de campo varian. Este articulo discute los criterios esenciales y efectivos que pueden ser utilizados para seleccionar un sistema de grabacion basado en las metas de investigacion y los recursos financieros disponibles. Para estudiar y hacer censos de aves tropicales, los biologos reconocen que es esencial poder identificar los pajaros por sus sonidos y tener las destrezas para hacer grabaciones de sus voces (Parker 1991). Aunque varias publicaciones sobre la preparacion de grabaciones de sonidos de aves han sido escritas para la investigacion (Gulledge 1976, Wickstrom 1982, Ranft 1991, Vielliard 1993), avances recientes en la tecnologia de grabacion, junto con los requerimientos especificos del investigador del tropico, ameritan revisar y poner al dia la informacion presentada en estas publicaciones. Este articulo presenta la informacion tecnica fundamental requerida para dominar la operacion de un sistema de grabaciones en el campo y prepara al grabador de sonidos de aves para situaciones que se pueden encontrar en los tropicos. THE IMPORTANCE OF Recording About 3,100 bird species (Ridgely and Tudor 1989), roughly a third of the world's bird species, occur on the continent of South America. Although much of the region's baseline natural history remains undocumented, the rate of habitat destruction is outpacing the ability of scientists to document and study these species and populations. The next decade offers a critical window of opportunity in which to document the voices of wildlife in the Neotropics before many disappear. Every researcher collecting sound Recordings in this region can make a unique contribution to bird research and conservation (Kroodsma et al. 1996a). Relative to temperate latitude birds, the biology of tropical species is little known. Recordings of their voices provide important baseline data for research in the fields of avian systematics, behavior, and bioacoustics, and are essential to conservation initiatives as training and playback tools for surveys and censuses.
Julius O Smith - One of the best experts on this subject based on the ideXlab platform.
-
perceptual spatial Audio Recording simulation and rendering an overview of spatial Audio techniques based on psychoacoustics
IEEE Signal Processing Magazine, 2017Co-Authors: Huseyin Hacihabiboglu, Enzo De Sena, Zoran Cvetkovic, James Johnston, Julius O SmithAbstract:Developments in immersive Audio technologies have been evolving in two directions: physically motivated systems and perceptually motivated systems. Physically motivated techniques aim to reproduce a physically accurate approximation of desired sound fields by employing a very high equipment load and sophisticated, computationally intensive algorithms. Perceptually motivated techniques, however, aim to render only the perceptually relevant aspects of the sound scene by means of modest computational and equipment load. This article presents an overview of perceptually motivated techniques, with a focus on multichannel Audio Recording and reproduction, Audio source and reflection culling, and artificial reverberators.