Ears of the Robot : Direction of Arrival Estimation Based on Pattern Recognition Using Robot-Mounted Microphones
スポンサーリンク
概要
- 論文の詳細を見る
We propose a new type of direction-of-arrival estimation method for robot audition that is free from strict head related transfer function estimation. The proposed method is based on statistical pattern recognition that employs a ratio of power spectrum amplitudes occurring for a microphone pair as a feature vector. It does not require any phase information explicitly, which is frequently used in conventional techniques, because the phase information is unreliable for the case in which strong reflections and diffractions occur around the microphones. The feature vectors we adopted can treat these influences naturally. The effectiveness of the proposed method was shown from direction-of-arrival estimation tests for 19 kinds of directions: 92.4% of errors were reduced compared with the conventional phase-based method.
- 2008-05-01
著者
-
Ogawa Tetsuji
Department of Endodontology and Periodontology, Hiroshima University School of Dentistry
-
Ogawa Tetsuji
Waseda Univ. Tokyo Jpn
-
Kobayashi Tetsunori
Waseda Univ. Tokyo Jpn
-
Kobayashi Tetsunori
Department Of Computer Science Waseda University
-
MOCHIKI Naoya
Department of Computer Science, Waseda University
-
Mochiki Naoya
Department Of Computer Science Waseda University
-
Kobayashi Tetsunori
Dep. Of Computer Sci. Waseda Univ.
-
OGAWA Tetsuji
Department of Computer Science, Waseda University
-
Ogawa Tetsuji
Department of Advanced General Dentistry, Hiroshima University Hospital
関連論文
- CENSREC-1-C : An evaluation framework for voice activity detection under noisy environments
- New Attachment to Periodontally Diseased Root Surfaces Treated with Hydrochloric Acid
- C-5 Interfacial Structure between Implant Materials and Periodontal Tissue in the Rat
- Cell-bound Pullulanase from Streptomyces sp. No.27
- Ears of the Robot : Direction of Arrival Estimation Based on Pattern Recognition Using Robot-Mounted Microphones
- Mutual Information Based Dynamic Integration of Multiple Feature Streams for Robust Real-Time LVCSR
- Filter Bank Subtraction for Robust Speech Recognition (Special Issue on Speech Information Processing)
- Simultaneous Subtitling System for Broadcast News Programs with a Speech Recognizer(Special Issue on the 2001 IEICE Excellent Paper Award)
- Influence of Lombard Effect : Accuracy Analysis of Simulation-Based Assessments of Noisy Speech Recognition Systems for Various Recognition Conditions
- A Low-Band Spectrum Envelope Reconstruction Method for PSOLA-Based F_0 Modification(Speech and Hearing)
- Fusion-Based Age-Group Classification Method Using Multiple Two-Dimensional Feature Extraction Algorithms(Pattern Recognition)
- Ears of the Robot : Three Simultaneous Speech Segregation and Recognition Using Robot-Mounted Microphones(Speech and Hearing)
- Genetic Algorithm Based Optimization of Partly-Hidden Markov Model Structure Using Discriminative Criterion(Speech Recognition, Statistical Modeling for Speech Processing)
- Hybrid Voice Conversion of Unit Selection and Generation Using Prosody Dependent HMM(Speech and Hearing)
- Extension of Hidden Markov Models for Multiple Candidates and Its Application to Gesture Recognition(Image Recognition, Computer Vision)
- Speech Enhancement Using a Square Microphone Array in the Presence of Directional and Diffuse Noise
- Ultrastructural and Immunocytochemical Characterization of the Bone-Single Crystal Sapphire Implant Interface in the Rat Maxilla
- Conversational robots: An approach to conversation protocol issues that utilizes the paralinguistic information available in a robot-human setting
- Prevalence of drug-resistant opportunistic microorganisms in oral cavity after treatment for oral cancer