Speech Enhancement Using a Square Microphone Array in the Presence of Directional and Diffuse Noise
スポンサーリンク
概要
- 論文の詳細を見る
We propose a new speech enhancement method suitable for mobile devices used in the presence of various types of noise. In order to achieve high-performance speech recognition and auditory perception in mobile devices, various types of noise have to be removed under the constraints of a space-saving microphone arrangement and few computational resources. The proposed method can reduce both the directional noise and the diffuse noise under the abovementioned constraints for mobile devices by employing a square microphone array and conducting low-computational-cost processing that consists of multiple null beamforming, minimum power channel selection, and Wiener filtering. The effectiveness of the proposed method is experimentally verified in terms of speech recognition accuracy and speech quality when both the directional noise and the diffuse noise are observed simultaneously; this method reduces the number of word errors and improves the log-spectral distances as compared to conventional methods.
- (社)電子情報通信学会の論文
- 2010-05-01
著者
-
Ogawa Tetsuji
Waseda Univ. Tokyo Jpn
-
Ogawa Tetsuji
Waseda Institute For Advanced Study Waseda University
-
Ogawa Tetsuji
Waseda Institute For Advanced Study
-
Kobayashi Tetsunori
Department Of Computer Science Waseda University
-
TAKADA Shintaro
Department of Computer Science, Waseda University
-
AKAGIRI Kenzo
Department of Computer Science, Waseda University
-
Akagiri Kenzo
Department Of Computer Science Waseda University
-
Takada Shintaro
Department Of Computer Science Waseda University
-
Ogawa Tetsuji
Waseda Inst. For Advanced Study Waseda Univ.
関連論文
- CENSREC-1-C : An evaluation framework for voice activity detection under noisy environments
- Ears of the Robot : Direction of Arrival Estimation Based on Pattern Recognition Using Robot-Mounted Microphones
- 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)
- 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
- CENSREC-4: An evaluation framework for distant-talking speech recognition in reverberant environments
- Conversational robots: An approach to conversation protocol issues that utilizes the paralinguistic information available in a robot-human setting