Prediction of fujisaki model's phrase commands

Abstract

This paper presents a model to predict the phrase commands of the Fujisaki Model for F0 contour for the Portuguese Language. Phrase commands location in text is governed by a set of weighted rules. The amplitude (Ap) and timing (T0) of the phrase commands are predicted in separate neural networks. The features for both neural networks are discussed. Finally a comparison between target and predicted values is presented.

Prediction of accent commands for the Fujisaki intonation model

“…In Figure 1 the AC-prediction model is applied over the set of labeled FCs. In Figure 2 both FCs and ACs are predicted by the developed methods presented in [1] and here, respectively. The English translation of the text presented in the Figures is: "… and are certainly important for all, particularly for those who have responsibilities …".…”

“…This paper reports the work related to a part of the prosody model for TTS that is under development for the European Portuguese (EP) language [1].…”

“…F0 is the most perceptually relevant component in prosody. The Fujisaki model for F0 contour has been proven to be well adapted, with very high naturalness, to several languages [2] like Japanese, Korean, Spanish, Polish, Greek, Swedish, English [3], German [4], Basque [5] and now also Portuguese [1] [6]. The model [2] consists of the logarithmic addition of baseline fundamental frequency, F b , phrase components and accent components.…”

Síntese de fala aplicada à geração de conjunto de dados para reconhecimento automático de fala

“…In turn, the duration estimator estimates the duration of each phoneme. Finally, the acoustic model receives the phoneme representation sequence, the prosodic information about phoneme segments' length, the F0 contour and computes the speech signal (Teixeira et al, 2003;. Several acoustic models have been proposed, such as the classical formant model (Klatt, 1980), Linear Prediction Coefficients (LPC) model, the Pitch Synchronous Overlap and Add (PSOLA) models (Charpentier & Stella, 1986) widely used in TTS engines like Microsoft Speech API.…”