512 search results - page 4 / 103 » Signal Processing for Robust Speech Recognition |
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
The problem of acoustic-to-articulatory speech inversion continues to be a challenging research problem which significantly impacts automatic speech recognition robustness and ac...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
Prior models of speech have been used in robust automatic speech recognition to enhance noisy speech. Typically, a single prior model is trained by pooling the entire training dat...
ICASSP
2008
IEEE
14 years 6 days ago
2008
IEEE
It has been shown that speech spectrograms can be read by trained experts. In this work, we regard the speech spectrogram image as a written text in some unknown language and perf...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
Recently there has been interest in structured discriminative models for speech recognition. In these models sentence posteriors are directly modelled, given a set of features ext...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
This paper addresses a noise suppression problem, namely the estimation of non-stationary noise sequences. In this problem, we assume that non-stationary noise can be decomposed i...