HMM-based speech synthesis adaptation using noisy data: Analysis and evaluation methods

Reima Karhila, Ulpu Remes, Mikko KurimoICASSP 2013 · OpenReview

Abstract

This paper investigates the role of noise in speaker-adaptation of HMM-based text-to-speech (TTS) synthesis and presents a new evaluation procedure. Both a new listening test based on ITU-T recommendation 835 and a perceptually motivated objective measure, frequency-weighted segmental SNR, improve the evaluation of synthetic speech when noise is present. The evaluation of voices adapted with noisy data show that the noise plays a relatively small but noticeable role in the quality of synthetic speech: Naturalness and speaker similarity are not affected in a significant way by the noise, but listeners prefer the voices trained from cleaner data. Noise removal, even when it degrades natural speech quality, improves the synthetic voice.
BibTeX
@inproceedings{karhila2013hmm,
  author = {Reima Karhila and Ulpu Remes and Mikko Kurimo},
  title = {{HMM-based speech synthesis adaptation using noisy data: Analysis and evaluation methods}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2013},
  url = {https://openreview.net/forum?id=gih4tqFPZy},
}

Loading related content...

Figure