In this paper, we extend our previous study on discriminative training using non-uniform criteria for speech recognition. The work will put emphasis on how the acoustic modeling i...
—Architectural schemes for low-power calibration of oversampled analog-to-digital (A/D) systems are presented. Conventional full-rate least-mean squares (LMS) calibration has two...
Subhanshu Gupta, Yi Tang, Kuang-Wei Cheng, Jeyanan...
This paper proposes a new multi-exposure fusion algorithm for HDR imaging. The advantage of the fusion based method is that it does not actually generate HDR images so that the co...
Jaehyun An, Sang Heon Lee, Jung Gap Kuk, Nam Ik Ch...
—Frame permutation quantization (FPQ) is a new vector quantization technique using finite frames. In FPQ, a vector is encoded using a permutation source code to quantize its fra...
One of the fundamental building blocks of text processing for textto-speech (TTS) synthesis is the assignment of a part-of-speech (POS) tag to each input word. POS tags are heavil...