For our experiments on meeting data we have used comparable recording conditions such as each speaker in the meeting has been wearing his or her own lapel microphone. Frequently however this assumption does not apply.
We have also carried out experiments aimed at producing obust recognition when microphones are positioned at varying distances from the speaker. In this case data, specific for the microphone distance and SNR found in the test condition is unavailable. We therefore apply a new method, Model Combination based Acoustic Mapping (MAM) originally proposed for recognition in different car noise environments to the recognition of speech at different distances. MAM estimates an acoustic mapping on the log-spectral domain in order to compensate for noise condition mismatches between training and test.

We applied MAM to data that was recorded simultaneously by an array of microphones positions at different distances from the speaker. Each speaker read several paragraphs of text from the Broadcast News corpus. Experiments suggest that MAM effectively models the signal condition found in the test resulting in substantial performance improvements.