Acoustic beamforming exploiting directionality of human speech sources
نویسندگان
چکیده
This paper examines the improvement that can be attained with perfect knowledge of the sound source directivity pattern and orientation in beamformer designs in the problem of speech acquisition. Data-independent beamformers are derived through formulation of a constrained optimization problem with a unity-gain constraint. Using computer simulation, these beamforming schemes are compared to the delay and sum (DS) beamformer and the best single sensor in a reverberant room environment. Criteria used to measure performance are (1) the direct to reverberant ratio, to assess extent of reverberation suppression, and (2) an objective measure of speech intelligibility called the speech transmission index (STI). For human-speaker source directivity, simulation results show that modest improvements to performance are obtainable.
منابع مشابه
Model-based Sparse Component Analysis for Multiparty Distant Speech Recognition
This thesis takes place in the context of multi-microphone distant speech recognition in multiparty meetings. It addresses the fundamental problem of overlapping speech recognition in reverberant rooms. Motivated from the excellent human hearing performance on such problem, possibly resulting of sparsity of the auditory representation, our work aims at exploiting sparse component analysis in sp...
متن کاملDistant Speech Recognition Experiments Using the AMI Corpus
This chapter reviews distant speech recognition experimentation using the AMI Corpus of multiparty meetings. The chapter compares conventional approaches using microphone array beamforming followed by single-channel acoustic modelling with approaches which combine multichannel signal processing with acoustic modelling in the context of convolutional networks.
متن کاملSimulation, Visulization and Perception of Sound in a Virtual Environment Using Beamforming
This paper describes a method to visualize and localize the sound that is simulated within a virtual environment using beamforming. The use of an acoustic camera along with noise image software as a short introduction to beamforming method is demonstrated. Furthermore, the transition from the three-dimensional sound recording to the three-dimensional virtual acoustic mapping, visualization and ...
متن کاملEffect of Directional Strategy on Audibility of Sounds in the Environment
Directional microphones in hearing aids have been well-documented to improve speech recognition in noise in laboratory conditions. The real-world perceived benefits of directionality have been less dramatic. The development of directional technology during the past decade has focused on improving laboratory benefit by means of adaptive behavior, and more recently, binaural beamforming made poss...
متن کاملImproving automatic speech recognition in spatially-aware hearing aids
In the context of ambient assisted living, automatic speech recognition (ASR) has the potential to provide textual support for hearing aid users in challenging acoustic conditions. In this paper we therefore investigate possibilities to improve ASR based on binaural hearing aid signals in complex acoustic scenes. Particularly, information about the spatial configuration of sound sources is expl...
متن کامل