The differenced-MMI (dMMI) is a discriminative criterion that generalizes MPE and BMMI.
We discuss the behavior of dMMI when there are errors in the transcription labels.
dMMI may be less sensitive to such errors than other criteria.
We support our claim with unsupervised speaker adaptation experiments.
dMMI based adaptation achieves significant gains over MLLR for 2 LVCSR tasks.