Validating different flexible vocabulary approaches on the Swiss French PolyPhone and PolyVar databases

Validates the flexible vocabulary approach for speaker-independent isolated-word and connected-word recognition. We compare the performance of classical whole-word HMMs against different sets of subword units. For this purpose, we model phonemes, diphones and words of the (Swiss) French language. The recognition rates obtained with phoneme models are monitored as we increase the amount of training data. The results of the described experiments validate the flexible vocabulary approach and show the advantages and disadvantages of both proposed subword units against common whole-word HMMs.