In the `missing data' approach to improving the robustness of automatic speech recognition to added noise, an initial process identifies spectraltemporal regions which are do...
Grounded language models represent the relationship between words and the non-linguistic context in which they are said. This paper describes how they are learned from large corpo...
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...
We present a proposal for an Automatic Speech Recognizer based on a “multigranular” model. The leading hypothesis is that speech signal contains information distributed on more...
Francesco Cutugno, Gianpaolo Coro, Massimo Petrill...