@conference{tts_is2011,
author = "Hanna Sil{\'e}n and Elina Helander and Moncef Gabbouj",
abstract = "In hidden Markov model-based speech synthesis, speech is
typically parameterized using source-filter decomposition. A
widely used analysis/synthesis framework, STRAIGHT, decomposes
the speech waveform into a framewise spectral envelope
and a mixed mode excitation signal. Inclusion of an
aperiodicity measure in the model enables synthesis also for
signals that are not purely voiced or unvoiced. In the traditional
approach employing hidden Markov modeling and decision
tree-based clustering, the connection between speech spectrum
and aperiodicities is not taken into account. In this paper,
we take advantage of this dependency and predict voice aperiodicities
afterwards based on synthetic spectral representations.
The evaluations carried out for English data confirm that the
proposed approach is able to provide prediction accuracy that is
comparable to the traditional approach.",
address = "Florence, Italy",
booktitle = "Interspeech",
keywords = "aperiodicity prediction;hidden Markov model;speech synthesis",
month = "August",
note = "Demo available at: https://www.cs.tut.fi/sgn/arg/silen/is2011/AperiodicityPrediction.html",
pages = "105 - 108",
title = "{P}rediction of voice aperiodicity based on spectral representations in {HMM} speech synthesis",
url = "https://www.cs.tut.fi/sgn/arg/silen/is2011/pdf/is2011-silen.pdf",
year = "2011",
}