Experiments in speaker normalisation and adaptation for large vocabulary speech recognition

This paper examines techniques for speaker normalisation and adaptation that are applied in training with the aim of removing some of the variability from the speaker independent models. Two techniques are examined: vocal tract normalisation (VTN) which estimates a single “vocal tract length” parameter for each speaker and then modifies the speech parameterisation accordingly and speaker adaptive training (SAT) which estimates Gaussian mean and variance parameters jointly with a speaker specific set of maximum likelihood linear regression (MLLR) based transformations. It is shown that VTN is effective for both clean speech and mismatched conditions and that the further improvements obtained by applying MLLR in testing are essentially additive. Detailed results from the use of SAT show that worthwhile improvements over using MLLR with standard speaker independent models are obtained