Testing the consistency assumption: Pronunciation variant forced alignment in read and spontaneous speech synthesis

Rasmus Dall, Sandrine Brognaux, Korin Richmond, Cassia Valentini-Botinhao, Gustav Eje Henter, Julia Hirschberg, Junichi Yamagishi, Simon King
2016 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Forced alignment for speech synthesis traditionally aligns a phoneme sequence predetermined by the front-end text processing system. This sequence is not altered during alignment, i.e., it is forced, despite possibly being faulty. The consistency assumption is the assumption that these mistakes do not degrade models, as long as the mistakes are consistent across training and synthesis. We present evidence that in the alignment of both standard read prompts and spontaneous speech this phoneme
more » ... uence is often wrong, and that this is likely to have a negative impact on acoustic models. A latticebased forced alignment system allowing for pronunciation variation is implemented, resulting in improved phoneme identity accuracy for both types of speech. A perceptual evaluation of HMM-based voices showed that spontaneous models trained on this improved alignment also improved standard synthesis, despite breaking the consistency assumption.
doi:10.1109/icassp.2016.7472660 dblp:conf/icassp/DallBRVHHYK16 fatcat:my6bkr3r6fdb3idder2vdw6l5a