Lin, Q., Yuk, D., de Vries, B., Parson, J., and Flanagan, J. Robust distanttalking speech recognition. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing 1996 I (1996), 21--24.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....Institute, April 1997 88 to reverse if no knowledge of the room response is available. In ASR applications, the efforts for reduction of the effects of reverberation have been mainly adaptations of techniques used for reverberation reduction in speech enhancement, such as microphone arrays [36], and channel identification and inversion procedures. Such techniques attempt to recover the speech signal with good perceptual quality and intelligibility. In ASR there is no need to resynthesize a speech signal, thus the short time phase of the signal is typically not required, and the exact ....

Lin, Q., Yuk, D., de Vries, B., Parson, J., and Flanagan, J. Robust distanttalking speech recognition. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing 1996 I (1996), 21--24.

....the patient s wrist position 60 times second, while the RMII provides 75 finger position updates second. a) b) Figure 1. Telerehabilitation workstation: a) prototype developed at Rutgers; b) The Rutgers Master II connected to the Multipurpose Haptic Control Interface The microphone array [13] provides hands free voice input by focusing on the patient s head siting approximately 3 feet in front of the monitor. The net camera connected to the PC parallel port is able to provide up to 15 fps QCIF images when running on a local machine. 3. Virtual Reality Rehabilitation Exercise Library ....

Q. Lin, C.-W. Che, D.-S. Yuk, & J. L. Flanagan, Robust Distant Talking Speech Recognition, Proceedings of ICASSP'96, Atlanta, GA, 1996, pp 21-24.

....this restriction, hands free devices are the right choice, but the recognition rate decreases dramatically, as the signal to noise ratio (SNR) decreases. Many publications address this problem with the focus on broad band, slowly varying noise. Single and multi microphone approaches are known [1, 2, 3, 4]. This contribution deals with the problem of a second speaker in the same room. Therefore, the interference signal is coloured and non stationary. For a two channel system a possible solution is published in [5] This algorithm is a derivation of a two channel generalized sidelobe canceller [6] ....

Q. Lin, C. Che, D. S. Yuk, L. Jin, B. Vries, J. Pearson, and J. Flanagan, "Robust distant-talking speech recognition, " in Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Proc. (ICASSP), vol. 1, pp. 21--24, 1996.

....every word of the utterance will be necessary to exactly determine where the user is pointing at (with tactile glove or mouse) while speaking. Furthermore, the Whisper system exclusively runs under Microsoft Windows and is not portable to different platforms. Therefore, a CAIP developed recognizer [4] will be applied to solve these problems. Microphone Array CAIP s microphone array technology liberates the user from body worn or hand held microphone equipment, permitting freedom of movement in the workplace. The current fixed focus line microphone array focuses on the speaker s head ....

....The current fixed focus line microphone array focuses on the speaker s head sitting approximately 3 feet from the monitor. Other sound sources are successfully attenuated. A CAIP developed microphone array system is applied as a robust front end for the speech recognizer to allow distant talking [4]. 3.2 Language Processing and Sensory Fusion Parser The first step in the understanding of multimodal commands involves parsing of the sensory inputs. In our system, the parser communicates with each modality and the fusion agent as illustrated in Fig 3. The reason for communicating through the ....

Q. Lin, C.-W. Che, D.-S. Yuk, and J. L. Flanagan, "Robust Distant Talking Speech Recognition, " Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'96), Atlanta, GA, pp.21-24, May 1996.

....to exactly determine where the user is pointing at (with tactile glove or mouse) while speaking. Furthermore, the Whisper system exclusively runs under Microsoft Windows and is not portable to different platforms. Therefore, a CAIP developed recognizer will be applied to solve these problems, see Lin (1996c) Hand Gestures Reading Software Agent commands RM II Screen Plane Glove position tracking MICROPHONE ARRAY Fig. 2. Hand gesture interaction and glove display. 3.4 Microphone Array CAIP s microphone array technology liberates the user from body worn or hand held microphone equipment, ....

....current fixed focus line microphone array focuses on the speaker s head sitting approximately 3 feet from the monitor. Other sound sources are successfully attenuated. A CAIP developed microphone array system is applied as a robust front end for the speech recognizer to allow distant talking, see Lin (1996c) 4 Language Processing and Sensory Fusion 4.1 Parser The first step in the understanding of multimodal commands involves parsing of the sensory inputs. In our system, the parser communicates with each modality and the fusion agent as illustrated in Fig 3. The reason for communicating through ....

Lin, Q., Che, C.-W., Yuk, D.-S. and Flanagan, J. L. (1996) Robust Distant Talking Speech Recognition.

....every word of the utterance will be necessary to exactly determine where the user is pointing at (with tactile glove or gaze) while speaking. Furthermore, the Whisper system exclusively runs under Microsoft Windows and is not portable to different platforms. Therefore, a CAIP developed recognizer [7] will be applied to solve these problems. Microphone Array CAIP s microphone array technology liberates the user from body worn or hand held microphone equipment, permitting freedom of movement in the workplace. The current fixed focus line microphone array focuses on the speaker s head sitting ....

....The current fixed focus line microphone array focuses on the speaker s head sitting approximately 3 feet from the monitor. Other sound sources are successfully attenuated. A CAIP developed microphone array system is applied as a robust front end for the speech recognizer to allow distant talking [7]. LANGUAGE PROCESSING AND SENSORY FUSION Parser The first step in the understanding of multimodal commands involves parsing of the sensory inputs. In our system, the parser communicates with each modality and the fusion agent as illustrated in Fig 4. The reason for communicating through the ....

Q. Lin, C.-W. Che, D.-S. Yuk, and J. L. Flanagan, "Robust Distant Talking Speech Recognition, " Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'96), Atlanta, GA, pp.21-24, May 1996.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC