TY - GEN
T1 - Improvement in listening capability for humanoid robot HRP-2
AU - Takahashi, Toru
AU - Nakadai, Kazuhiro
AU - Komatani, Kazunori
AU - Ogata, Tetsuya
AU - Okuno, Hiroshi G.
PY - 2010/8/26
Y1 - 2010/8/26
N2 - This paper describes improvement of sound source separation for a simultaneous automatic speech recognition (ASR) system of a humanoid robot. A recognition error in the system is caused by a separation error and interferences of other sources. In separability, an original geometric source separation (GSS) is improved. Our GSS uses a measured robot's head related transfer function (HRTF) to estimate a separation matrix. As an original GSS uses a simulated HRTF calculated based on a distance between microphone and sound source, there is a large mismatch between the simulated and the measured transfer functions. The mismatch causes a severe degradation of recognition performance. Faster convergence speed of separation matrix reduces separation error. Our approach gives a nearer initial separation matrix based on a measured transfer function from an optimal separation matrix than a simulated one. As a result, we expect that our GSS improves the convergence speed. Our GSS is also able to handle an adaptive step-size parameter. These new features are added into open source robot audition software (OSS) called "HARK" which is newly updated as version 1.0.0. The HARK has been installed on a HRP-2 humanoid with an 8-element microphone array. The listening capability of HRP-2 is evaluated by recognizing a target speech signal which is separated from a simultaneous speech signal by three talkers. The word correct rate (WCR) of ASR improves by 5 points under normal acoustic environments and by 10 points under noisy environments. Experimental results show that HARK 1.0.0 improves the robustness against noises.
AB - This paper describes improvement of sound source separation for a simultaneous automatic speech recognition (ASR) system of a humanoid robot. A recognition error in the system is caused by a separation error and interferences of other sources. In separability, an original geometric source separation (GSS) is improved. Our GSS uses a measured robot's head related transfer function (HRTF) to estimate a separation matrix. As an original GSS uses a simulated HRTF calculated based on a distance between microphone and sound source, there is a large mismatch between the simulated and the measured transfer functions. The mismatch causes a severe degradation of recognition performance. Faster convergence speed of separation matrix reduces separation error. Our approach gives a nearer initial separation matrix based on a measured transfer function from an optimal separation matrix than a simulated one. As a result, we expect that our GSS improves the convergence speed. Our GSS is also able to handle an adaptive step-size parameter. These new features are added into open source robot audition software (OSS) called "HARK" which is newly updated as version 1.0.0. The HARK has been installed on a HRP-2 humanoid with an 8-element microphone array. The listening capability of HRP-2 is evaluated by recognizing a target speech signal which is separated from a simultaneous speech signal by three talkers. The word correct rate (WCR) of ASR improves by 5 points under normal acoustic environments and by 10 points under noisy environments. Experimental results show that HARK 1.0.0 improves the robustness against noises.
UR - http://www.scopus.com/inward/record.url?scp=77955834429&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77955834429&partnerID=8YFLogxK
U2 - 10.1109/ROBOT.2010.5509830
DO - 10.1109/ROBOT.2010.5509830
M3 - Conference contribution
AN - SCOPUS:77955834429
SN - 9781424450381
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 470
EP - 475
BT - 2010 IEEE International Conference on Robotics and Automation, ICRA 2010
T2 - 2010 IEEE International Conference on Robotics and Automation, ICRA 2010
Y2 - 3 May 2010 through 7 May 2010
ER -