Intelligent sound source localization for dynamic environments

Nakamura, Keisuke; Nakadai, Kazuhiro; Asano, Futoshi; Hasegawa, Yuji; Tsujino, Hiroshi

doi:10.1109/iros.2009.5354419

Cited by 83 publications

(35 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The ego-centric distance is calculated by Equation (1). The error of the estimated ego-centric distance is below 0.02 m over the range from 0.5 m to 1.5 m after correction.…”

Section: Experimental Measuring Systemmentioning

confidence: 99%

“…The audition of humanoid robots has conventionally been an array system and not a binaural system. As an example of an array system, multiple lightweight microphones are mounted on the head of humanoid robots ASIMO (Advanced Steps in Innovative Mobility) and HRP-2 (Humanoid Robotics Project-2) [1,2]. Multiple microphones are necessary for realizing multiple acoustical functions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Room Volume Estimation Based on Ambiguity of Short-Term Interaural Phase Differences Using Humanoid Robot Head

Shimoyama

Fukuda

2016

Robotics

View full text Add to dashboard Cite

Abstract:Humans can recognize approximate room size using only binaural audition. However, sound reverberation is not negligible in most environments. The reverberation causes temporal fluctuations in the short-term interaural phase differences (IPDs) of sound pressure. This study proposes a novel method for a binaural humanoid robot head to estimate room volume. The method is based on the statistical properties of the short-term IPDs of sound pressure. The humanoid robot turns its head toward a sound source, recognizes the sound source, and then estimates the ego-centric distance by its stereovision. By interpolating the relations between room volume, average standard deviation, and ego-centric distance experimentally obtained for various rooms in a prepared database, the room volume was estimated by the binaural audition of the robot from the average standard deviation of the short-term IPDs at the estimated distance.

show abstract

“…The ego-centric distance is calculated by Equation (1). The error of the estimated ego-centric distance is below 0.02 m over the range from 0.5 m to 1.5 m after correction.…”

Section: Experimental Measuring Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Room Volume Estimation Based on Ambiguity of Short-Term Interaural Phase Differences Using Humanoid Robot Head

Shimoyama

Fukuda

2016

Robotics

View full text Add to dashboard Cite

show abstract

“…To solve this problem, HARK extended conventional MUSIC by applying generalized eigenvalue decomposition (GEVD) and generalized singular value decomposition (GSVD), i.e., GEVD-MUSIC and GSVD-MUSIC, respectively [27]. These methods use knowledge about noise sources stored in a noise correlation matrix calculated from noise signals captured in advance.…”

Section: Sound Source Localizationmentioning

confidence: 99%

Robot audition: Its rise and perspectives

Okuno

Nakadai

2015

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

The ability of robots to listen to several things at once with their own "ears", that is, robot audition, is an important factor in improving interaction and symbiosis between humans and robots. The critical issue in robot audition is real-time processing and robustness against noisy environments with high flexibility to support various kinds of robots and hardware configurations. This paper first overviews activities and issues related to robot audition. Then, it presents the "HARK" robot audition software, which provides three primary functions for robot audition, sound source localization, sound source separation, and separated sound recognition, and then reports their performance. Finally, it discusses future directions in new promising areas as well as robotics.

show abstract

“…The noise used here is diffuse noise; directional noise might create peaks in the MUSIC spectrum. To remove any peaks created by directional noise, we use a GEVD-MUSIC algorithm [8] with additional information for noise: a noise correlation matrix. Let's take a look at these algorithms in detail.…”

Section: Music and Gevd-music Algorithmsmentioning

confidence: 99%

“…A generalized eigenvalue decomposition-based multiple signal classification (GEVD-MUSIC) algorithm [8] reduces the effect of ego noise. The GEVD-MUSIC algorithm uses a spatial correlation matrix of the noise component to cancel the noise signal during yielding the DOA spectrum.…”

Section: Introductionmentioning

confidence: 99%

Noise correlation matrix estimation for improving sound source localization by multirotor UAV

Furukawa

Okutani

Nagira

et al. 2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

Abstract-A method has been developed for improving sound source localization (SSL) using a microphone array from an unmanned aerial vehicle with multiple rotors, a "multirotor UAV". One of the main problems in SSL from a multirotor UAV is that the ego noise of the rotors on the UAV interferes with the audio observation and degrades the SSL performance. We employ a generalized eigenvalue decomposition-based multiple signal classification (GEVD-MUSIC) algorithm to reduce the effect of ego noise. While GEVD-MUSIC algorithm requires a noise correlation matrix corresponding to the auto-correlation of the multichannel observation of the rotor noise, the noise correlation is nonstationary due to the aerodynamic control of the UAV. Therefore, we need an adaptive estimation method of the noise correlation matrix for a robust SSL using GEVD-MUSIC algorithm. Our method uses a Gaussian process regression to estimate the noise correlation matrix in each time period from the measurements of self-monitoring sensors attached to the UAV such as the pitch-roll-yaw tilt angles, xyz speeds, and motor control values. Experiments compare our method with existing SSL methods in terms of precision and recall rates of SSL. The results demonstrate that our method outperforms existing methods, especially under high signal-to-noise-ratio conditions.

show abstract

Intelligent sound source localization for dynamic environments

Cited by 83 publications

References 8 publications

Room Volume Estimation Based on Ambiguity of Short-Term Interaural Phase Differences Using Humanoid Robot Head

Room Volume Estimation Based on Ambiguity of Short-Term Interaural Phase Differences Using Humanoid Robot Head

Robot audition: Its rise and perspectives

Noise correlation matrix estimation for improving sound source localization by multirotor UAV

Contact Info

Product

Resources

About