ICASSP
2011
IEEE
13 years 8 days ago
2011
IEEE
An acoustic-phonetics based word-independent technique which uses syllable context for classifying the lexical syllable stress of spoken English words is presented. Nucleus based ...
ICASSP
2011
IEEE
13 years 8 days ago
2011
IEEE
Due to multipath delay spread and relatively high sampling rate in OFDM systems, the channel estimation is formulated as a sparse recovery problem, where a hybrid compressed sensi...
ICASSP
2011
IEEE
13 years 8 days ago
2011
IEEE
We propose the Arabic Chat Alphabet (ACA) as naturally written in everyday life for dialectal Arabic speech transcription. Our assumption is that ACA is a natural language that in...
ICASSP
2011
IEEE
13 years 8 days ago
2011
IEEE
Since optimum diversity behavior can be achieved, equalization based on lattice basis reduction is of special interest for transmission over MIMO channels. Although the per-symbol...
ICASSP
2011
IEEE
13 years 8 days ago
2011
IEEE
Color is a powerful attribute that is used to characterize objects for tracking and other surveillance tasks. Since color is dependent on ambient illumination and the imaging equi...
ICASSP
2011
IEEE
13 years 8 days ago
2011
IEEE
This paper consider the problem of how to evaluate the efficiency of a 3D continuous functional HRTF model in representing measured data. The proposed method is based on Karhunen...
ICASSP
2011
IEEE
13 years 8 days ago
2011
IEEE
We address a Kalman-like estimator for solving universally the problems of filtering (p = 0), prediction (p > 0), and smoothing (p < 0) of discrete time-varying state-space...
ICASSP
2011
IEEE
13 years 8 days ago
2011
IEEE
ICASSP
2011
IEEE
13 years 8 days ago
2011
IEEE
We present techniques for processing MPEG-audio encoded signals during the decoding process, using efficient fixed-point arithmetic operations. A large signal-to-quantization-no...
ICASSP
2011
IEEE
13 years 8 days ago
2011
IEEE
Assuming that a set of source signals is sparsely representable in a given dictionary, we show how their sparse recovery fails whenever we can only measure a convolved observation...