Showing papers by "R. De Mori published in 2000"
01 Jan 2000
TL;DR: The state-of-the-art for automatic speech recognition in automated Directory Assistance at the start of the 5th Framework project SMADA is summarized and the lines along which the research in SMADA will develop are indicated.
Abstract: In this paper we summarise the state-of-the-art for automatic speech recognition in automated Directory Assistance at the start of the 5th Framework project SMADA. Details are given about robust acoustic features for use in Distributed Speech Recognition, especially with respect to noise suppression. Then an overview is given of the confidence measures which are in use today, and their similarities and differences. Finally, work aimed at automatic update of acoustic models and automatic inference of language models is sketched that is becoming possible thanks to the very large amounts of data that can be recorded in operational services. In addition to summarising the state-of-the-art the paper also indicates the lines along which the research in SMADA will develop.
18 citations
05 Jun 2000
TL;DR: The paper provides a theoretical justification that gravity centers in frequency bands computed from zero-crossing information are far more robust to additive telephone noise than GCs computed from FFT spectra.
Abstract: The paper provides a theoretical justification that gravity centers (GC) in frequency bands computed from zero-crossing information are far more robust to additive telephone noise than GCs computed from FFT spectra. Experiments on two different corpora confirm the theoretical results when GCs are added to standard mel frequency-scaled cepstral coefficients (MFCC) and their time derivatives. A 20.1% word error reduction is observed on a large telephone corpus of Italian cities, with an average signal-to-noise ratio (SNR) of 15 dB, if GCs are computed from zero-crossings, while performance deteriorates when GCs are computed from FFT spectra.
7 citations