Noise in HMM-Based Speech Synthesis Adaptation: Analysis, Evaluation Methods and Experiments

@article{Karhila2014NoiseIH,
  title={Noise in HMM-Based Speech Synthesis Adaptation: Analysis, Evaluation Methods and Experiments},
  author={Reima Karhila and Ulpu Remes and Mikko Kurimo},
  journal={IEEE Journal of Selected Topics in Signal Processing},
  year={2014},
  volume={8},
  pages={285-295}
}
This work describes experiments on using noisy adaptation data to create personalized voices with HMM-based speech synthesis. We investigate how environmental noise affects feature extraction and CSMAPLR and EMLLR adaptation. We investigate effects of regression trees and data quantity and test noise-robust feature streams for alignment and NMF-based source separation as preprocessing. The adaptation performance is evaluated using a listening test developed for noisy synthesized speech. The… CONTINUE READING
Highly Cited
This paper has 31 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 12 extracted citations

Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2018
View 8 Excerpts
Method Support
Highly Influenced

Robust TTS duration modelling using DNNS

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2016
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 36 references

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

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 10 Excerpts
Highly Influenced

Maximum likelihood linear transformations for HMM-based speech recognition

Computer Speech & Language • 1998
View 5 Excerpts
Highly Influenced

Statistical Parametric Speech Synthesis Based on Speaker and Language Factorization

IEEE Transactions on Audio, Speech, and Language Processing • 2012
View 1 Excerpt

Speaker similarity evaluation of foreign-accented speech synthesis using HMM-based speaker adaptation

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2011
View 1 Excerpt