Public deliverables

Internship reports


Academic publications

Show all

Tuomo Raitio, Antti Suni, Lauri Juvela, Martti Vainio, Paavo Alku (2014): Deep neural network based trainable voice source model for synthesis of speech with varying vocal effort. In: Proc. Interspeech 2014, pp. 1969-1973, Singapore, 2014. (Type: Inproceeding | Links | BibTeX | Tags: Deep neural network, DNN, glottal flow, Speech synthesis, Vocal effort, voice source modelling)
Tuomo Raitio, Antti Suni, Martti Vainio, Paavo Alku (2013): Synthesis and Perception of Breathy, Normal, and Lombard Speech in the Presence of Noise. In: Special issue of Computer Speech and Language on 'The Listening Talker', 2013. (Type: Article | Abstract | Links | BibTeX | Tags: Adaptation, Breathy speech, intelligibility, Lombard speech, statistical parametric speech synthesis, Vocal effort)