No abstract

Robustness for speech recognition technologies with respect to adverse environments bas been a key issue for real applications. Time-frequency principal components (TFPC) features were shown to be a set of powerful data-driven features under matched circumstances, while histogram equalization (HEQ) was proposed as an efficient feature transformation approach to reduce the mismatch between training and testing conditions, In this paper, it is proposed that TFPC features can be well integrated with HEQ. HEQ generates a well-matched environment, in which TFPC features can be properly utilized. Extensive experiments with respect to the AURORA2 database verified that improved performance in adverse circumstances can be achieved.

No abstract

No abstract

A SoC, integrating RF/AFE and 1.5 Gb/s SATA PHY, is presented. It supports 471 Mb/s bit-rate at 18xS DVD. A partial parity mode reduces SDRAM bandwidth. A power control mode minimizes system clock rate. The SoC has 10M transistors, occupies 5.4 x 5.1 mm 2 in 0.18 mm CMOS process, and consumes 772 mW during 16xS DVD read.