Ling-Hui Chen, Tuomo Raitio, Cassia Valentini-Botinhao, Junichi Yamagishi, Zhen-Hua Ling (2014): DNN-based stochastic postfilter for HMM-based speech synthesis. In: Proc. Interspeech 2014, pp. 1954-1958, Singapore, 2014. (Type: Inproceeding | Links | BibTeX | Tags: DNN, HMM, modulation spectrum, postfilter, segmental quality, Speech synthesis)@inproceedings{Chen2014,
title = {DNN-based stochastic postfilter for HMM-based speech synthesis},
author = {Ling-Hui Chen and Tuomo Raitio and Cassia Valentini-Botinhao and Junichi Yamagishi and Zhen-Hua Ling},
url = {http://consortium.simple4all.org/files/2014/10/chen14.pdf},
year = {2014},
date = {2014-09-14},
booktitle = {Proc. Interspeech 2014},
pages = {1954-1958},
address = {Singapore},
keywords = {DNN, HMM, modulation spectrum, postfilter, segmental quality, Speech synthesis}
}
|
Stig-Arne Grönroos, Sami Virpioja, Peter Smit, Mikko Kurimo (2014): Morfessor FlatCat: An HMM-Based Method for Unsupervised and Semi-Supervised Learning of Morphology. In: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics, pp. 1177–1185, Dublin City University and Association for Computational Linguistics, Dublin, Ireland, 2014. (Type: Inproceeding | Links | BibTeX | Tags: HMM, machine learning, morfessor, morphology)@inproceedings{Gronroos2014,
title = {Morfessor FlatCat: An HMM-Based Method for Unsupervised and Semi-Supervised Learning of Morphology},
author = {Stig-Arne Grönroos and Sami Virpioja and Peter Smit and Mikko Kurimo},
url = {http://www.aclweb.org/anthology/C/C14/C14-1111.pdf},
year = {2014},
date = {2014-08-23},
booktitle = {Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics},
pages = {1177--1185},
publisher = {Dublin City University and Association for Computational Linguistics},
address = {Dublin, Ireland},
keywords = {HMM, machine learning, morfessor, morphology}
}
|
Bajibabu Bollepalli, Tuomo Raitio, Paavo Alku (2013): Effect of MPEG Audio Compression on HMM-based Speech Synthesis. In: Proc. Interspeech 2013, 2013. (Type: Inproceeding | Abstract | BibTeX | Tags: GlottHMM, HMM, MP3, Speech synthesis)@inproceedings{Bajibabu_IS13,
title = {Effect of MPEG Audio Compression on HMM-based Speech Synthesis},
author = {Bajibabu Bollepalli and Tuomo Raitio and Paavo Alku},
year = {2013},
date = {2013-04-25},
booktitle = {Proc. Interspeech 2013},
abstract = {In this paper, the effect of MPEG audio compression on HMM-based speech synthesis is studied. Speech signals are encoded with various compression rates and analyzed using the mboxGlottHMM vocoder. Objective evaluation results show that the vocoder parameters start to degrade from encoding with bit-rates of 32 kbit/s or less, which is also confirmed by the subjective evaluation of the vocoder analysis-synthesis quality. Experiments with HMM-based speech synthesis show that the subjective quality of a synthetic voice trained with 32 kbit/s speech is comparable to a voice trained with uncompressed speech, but lower bit rates induce clear degradation in quality.},
keywords = {GlottHMM, HMM, MP3, Speech synthesis}
}
In this paper, the effect of MPEG audio compression on HMM-based speech synthesis is studied. Speech signals are encoded with various compression rates and analyzed using the mboxGlottHMM vocoder. Objective evaluation results show that the vocoder parameters start to degrade from encoding with bit-rates of 32 kbit/s or less, which is also confirmed by the subjective evaluation of the vocoder analysis-synthesis quality. Experiments with HMM-based speech synthesis show that the subjective quality of a synthetic voice trained with 32 kbit/s speech is comparable to a voice trained with uncompressed speech, but lower bit rates induce clear degradation in quality.
|
Bajibabu Bollepalli, Jerome Urbain, Tuomo Raitio, Joakim Gustafson, Huseyin Cakmak (2013): A Comparative Evaluation of Vocoding Techniques for HMM-based Laughter Synthesis. In: Proc. ICASSP 2013, 2013. (Type: Inproceeding | BibTeX | Tags: DSM, GlottHMM, HMM, HTS, Laughter synthesis, mel-cepstrum, STRAIGHT, vocoder)@inproceedings{Bollepalli2014_laughter,
title = {A Comparative Evaluation of Vocoding Techniques for HMM-based Laughter Synthesis},
author = {Bajibabu Bollepalli and Jerome Urbain and Tuomo Raitio and Joakim Gustafson and Huseyin Cakmak},
year = {2013},
date = {2013-01-14},
booktitle = {Proc. ICASSP 2013},
keywords = {DSM, GlottHMM, HMM, HTS, Laughter synthesis, mel-cepstrum, STRAIGHT, vocoder}
}
|