Towards robot audition
نویسنده
چکیده
We discuss biologically inspired techniques for processing sound with a view to solving the what and where tasks. Starting from an auditorynerve like representation, we discuss an onset grouping technique for determining when to compute interaural time and intensity differences, and hence find the direction (where) of the source even in the presence of reflections. We have not yet implemented the what task, and we discuss some possible strategies.
منابع مشابه
Towards the Development of Robot Musical Audition
We are seeking to enable humanoid robots to participate in live human-robot musical ensembles. In ensembles, the musicians must be able to listen to the audio that they and the others are producing in order to identify high-level features of the music (e.g., location in the score, tempo, cues). This information is crucial for the musicians so that they can know what to play next. One requiremen...
متن کاملRobot Audition – Hands - Free Automatic Speech Recognition under Highly - Noisy Environemnts – Kazuhiro NAKADAI
This paper addresses robot audition, which realizes listening capabilities for robots using robot-embedded microphones. For robot audition, we propose real-time sound source separation and automatic speech recognition (ASR) techniques for dynamically changing environments based on microphone array processing, which is applicable to hands-free ASR under highly-noisy environments. Implementation ...
متن کاملAudition: the most important sense for humanoid robots?
In this paper, we introduce NAO, the humanoid robot developed by Aldebaran Robotics. For this robot, dedicated to be a companion, the interaction with humans is crucial and the audition appears to be a very important sense while the robotic community has been focusing on vision for a long time. Some of the developments on audio are presented.
متن کاملReliable Detection of Sound’s Direction for Active Audition
In this paper, we propose reliable detection of sound’s direction for human robot interaction. Compared with previous researches, this system comprises simpler algorithm and a proposed nonlinear amplifier which has advantages to increase a detectible distance of sound signal in spite of simple circuits. Moreover, we propose the new performance index using cross-correlation to make reliable dete...
متن کاملBlind Source Separation for Robot Audition Using Fixed Beamforming with HRTFs
We present a two stage blind source separation (BSS) algorithm for robot audition. The algorithm is based on a beamforming preprocessing and a BSS algorithm using a sparsity separation criterion. Before the BSS step, we filter the sensors outputs by beamforming filters to reduce the reverberation and the environmental noise. As we are in a robot audition context, the manifold of the sensor arra...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2005