1. |
- Dahl, Mattias, et al.
(author)
-
A Neural Network Trained Microphone Array System for Noise Reduction
- 1996
-
Conference paper (peer-reviewed)abstract
- This paper presents a neural network based microphone array system, which is capable to continuously perform speech enhancement and adaptation to nonuniform quantization, such as A-law and $mu@-law. Such a quantizer is designed to increase the Signal to Quantization Noise Ratio (SQNR) for small amplitudes in telecommunications systems. The proposed method primarily developed for hands-free mobile telephones, suppresses the ambient car noise with approximately 10 dB. The system is based upon a multi-layered nonlinear back-propagation trained network by using a built-in calibration technique.
|
|
2. |
- Dahl, Mattias, et al.
(author)
-
Acoustic Echo and Noise Cancelling using Microphone Arrays
- 1996
-
Conference paper (peer-reviewed)abstract
- This paper presents a new method to simultaneously perform 20 dB acoustic echo cancellation and 10 dB speech enhancement utilizing an adaptive microphone array. The system is based on a fast and efficient on-site calibration. Primarily intended for handsfree telephones in automobiles, the microphone array system simultaneously emphasizes the near-end talker and suppresses the handsfree loudspeaker and car noise. The method can also be used in other situations such as conventional speaker phones.
|
|
3. |
|
|
4. |
- Nordberg, Jörgen, et al.
(author)
-
Acoustic Echo Cancellation Employing Delayless Subband Adaptive Filters
- 1996
-
Conference paper (peer-reviewed)abstract
- The use of hands-free communication in cars, computer applications and video conferencing has created a demand for high-quality acoustic echo cancellation. In these applications these acoustic channel has typically a long impulse response in the order of 100ms. Typical lengths of adaptive FIR-filters can be 500-1500 taps. In order to reduce the complexity and also to improve the convergence rate, subband processing schemes have been suggested. This paper presents an implementation of a delayless subband adaptive filter. The study shows a possible suppression of about 30 dB and also a more rapid convergence compared to a fullband LMS-filter.
|
|