Academia Sinica

Yuan Ze University

Cortina Systems Corporation

Imedi Plus Inc.

Yu Tsao

Chih-Hsien Hsu

Xi Chen

Xiaochong Cao

Kun-Hsi Tsai

Yu-Cheng Su

Shih-Hsuan Ku

Syu-Siang Wang

Tzu-Chen Liang

Yung-Chung Liu

Yun-Fan Chang

Shih-I Yang

Chien-Chih Chen

Chien Hsiung Chang

Shih Hau Fang

Yao Shiao

Ying-Ren Chien

A system is provided to realize suppression by selecting wavelets for feature compression in distributed speech recognition. The system comprises a first device and a second device. The first device comprising: a first network module for connecting to a network; an acoustic transducer module for recording speech and outputting frames of recorded signal; and a first processor configured for the following: extracting multiple-dimensional speech features from the frames of the recorded signal to generate multiple feature sequences; applying discrete wavelet transform (DWT) to the feature sequences to obtain a plurality of component data; and transmitting at least one of the plurality of component data via the network, wherein another one of the plurality of component data is not transmitted. The second device comprising: a second network module for connecting to the network and receiving the at least one of the plurality of component data from the first device; and a second processor configured for the following: updating the received data to generate an updated data; and applying inverse discrete wavelet transform (IDWT) to the updated data to obtain reconstructed speech data.

System and methods for suppression by selecting wavelets for feature compression in distributed speech recognition

The present disclosure illustrates an acoustic echo cancellation method and system using the same. The acoustic echo cancellation method comprises the following steps. Firstly, a prior-knowledge matrix comprising a plurality of space vectors is built. Then, an initial filter vector is generated by the prior-knowledge matrix and an initial weighting vector. The weighting vector is updated based on the difference of the echo signal and the estimated signal in an iteration algorithm, and the coefficient of the filter vector is updated according to the updated weighting vector. An estimated signal is generated according to the updated filter vector and the original signal. Finally, the next echo signal is cancelled by the near-end estimated signal.

Acoustic echo cancellation method and system using the same

A system for recognizing physiological sound comprises a receiving module, a feature extracting module, a classifier, and a comparing module. A method for recognizing physiological sound comprises receiving a physiological sound by the receiving module; extracting at least one feature from the physiological sound by the feature extraction module; classifying the at least one feature to identify at least one category by a classifier; and comparing the at least one category with a normal physiological sound and/or an abnormal physiological sound by the comparing module for evaluating a risk of disease. The method and system for recognizing physiological sound can precisely identify the specific physiological sound and exclude the noise.

Method and system for recognizing physiological sound

High-speed networking application equipments with a layer-2 to layer-7 hardware search engine and method are with flexibility and performance improvement. The multi-layer switches/routers, network address translation (NAT) gateway, firewall/VPN router and network attached storage (NAS) may use the search engine for fast and efficient search requirement.

Apparatus and method for layer-2 to layer-7 search engine for high speed network application

Growing community of inventors

Taipei, Taiwan

Yu Tsao