Duration modeling in a restricted-domain female-voice synthesis in Spanish using neural networks

Córdoba, Ricardo de; Montero, Juan Manuel; Gutiérrez-Arriola, Juana M.; Pardo, José Manuel

doi:10.1109/icassp.2001.941034

Cited by 3 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have applied the same methodology to a female speaker in a restricted-domain environment (Córdoba et al, 2001). The most remarkable differences with the unrestricted-domain database presented in this paper are the following: the improvements are bigger, up to 5%; all position and "number of units" parameters give consistent improvements (between 2 and 3·5%); syllable structure and function word mean an improvement close to 2·5%; the parameters related to phrase provide better results; the best parameter is "position of the word in the phrase"; and the window of five phonemes for the phonemes identity is 5% better than the window of three phonemes.…”

Section: Summary Of Results For Parameter Evaluationmentioning

confidence: 99%

“…The detailed figures of our database are shown in Table I. Throughout the paper we will also mention the results we have obtained in similar experiments using a female speaker in a restricted-domain environment (Córdoba, Montero, Gutierrez-Arriola & Pardo, 2001). This restricted-domain offers several advantages to the modelling: the variation in the different patterns is reduced, and there are more instances of each vector of parameters in the database.…”

Section: Contentsmentioning

confidence: 99%

See 1 more Smart Citation

Selection of the most significant parameters for duration modelling in a Spanish text-to-speech system using neural networks

Córdoba

Montero

Gutiérrez

et al. 2002

Computer Speech & Language

View full text Add to dashboard Cite

Accurate prediction of segmental duration from text in a text-to-speech system is difficult for several reasons. One which is especially relevant is the great quantity of contextual factors that affect timing and it is difficult to find the right way to model them. There are many parameters that affect duration, but not all of them are always relevant and some can even be counterproductive because of the possibility of overtraining.The main motivation of this paper has been to reduce the error in the duration estimation. To this end, it is of the utmost importance to find the factors that most influence duration in a given language. The approach we have taken is to use a neural network, which is completely configurable, and experiment with the different combinations of parameters that yield the minimum error in the estimation.We have oriented our work mainly towards the following aspects: the most significant parameters that can be used as input to the automatic model, and the best way to code these parameters. We have studied first the effect of each parameter alone and, after that, we have included all parameters together to have our final system.Another important aspect of this study is the generation of a suite of software tools and design protocols that will be used in future tasks with different speakers and databases. The applications for automatic modelling are obvious: adapt the prosody to a new speaker, to a new environment, to "restricted-domain" sentences, etc., in a fast, semi-automatic and inexpensive way. After the database labelling, it is a matter of minutes to prepare the inputs to the network for the new situation, and the network is trained in 1 h.The result has been a system that predicts duration with very good results (19 ms in RMS) and that clearly improves our previous rule-based system.

show abstract

Section: Summary Of Results For Parameter Evaluationmentioning

confidence: 99%

Section: Contentsmentioning

confidence: 99%

Selection of the most significant parameters for duration modelling in a Spanish text-to-speech system using neural networks

Córdoba

Montero

Gutiérrez

et al. 2002

Computer Speech & Language

View full text Add to dashboard Cite

show abstract

“…Furthermore, artificial neural networks (Campbell 1992;Cordoba et al 2001), Bayesian networks models (Chien and Huang 2003;Goubanova and King 2008)) and instance-based algorithms (Lazaridis et al 2007) have also been introduced on the phone duration modeling task. In the following, we briefly mention some of the most frequently and successfully used methods for phone duration modeling (cf.…”

Section: Data-driven Techniquesmentioning

confidence: 99%

Phone duration modeling: overview of techniques and performance optimization via feature selection in the context of emotional speech

Lazaridis

Ganchev

Κωστούλας

et al. 2010

Int J Speech Technol

View full text Add to dashboard Cite

Accurate modeling of prosody is prerequisite for the production of synthetic speech of high quality. Phone duration, as one of the key prosodic parameters, plays an important role for the generation of emotional synthetic speech with natural sounding. In the present work we offer an overview of various phone duration modeling techniques, and consequently evaluate ten models, based on decision trees, linear regression, lazy-learning algorithms and metalearning algorithms, which over the past decades have been successfully used in various modeling tasks. Furthermore, we study the opportunity for performance optimization by applying two feature selection techniques, the RReliefF and the Correlation-based Feature Selection, on a large set of numerical and nominal linguistic features extracted from text, such as: phonetic, phonologic and morphosyntactic ones, which have been reported successful on the phone and syllable duration modeling task. We investigate the practical usefulness of these phone duration modeling techniques on a Modern Greek emotional speech database, which consists of five categories of emotional speech: anger, fear, joy, neutral, A. Lazaridis ( ) · T. Ganchev · T. Kostoulas · I. Mporas · N. Fakotakis sadness. The experimental results demonstrated that feature selection significantly improves the accuracy of phone duration prediction regardless of the type of machine learning algorithm used for phone duration modeling. Specifically, in four out of the five categories of emotional speech, feature selection contributed to the improvement of the phone duration modeling, when compared to the case without feature selection. The M5p trees based phone duration model was observed to achieve the best phone duration prediction accuracy in terms of RMSE and MAE.

show abstract

“…In German, a significant work has been done in [15], by capturing the types of interaction patterns affecting the duration. Neural network is used to predict the segmental duration in [16]. Objective evaluation of the model gave root mean squared error (RMSE) of 0.4536.…”

Section: Introductionmentioning

confidence: 99%

Duration modeling for text to speech synthesis system using festival speech engine developed for Malayalam language

Rajan

Rijoy

Gopinath³

et al. 2015

2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015]

View full text Add to dashboard Cite

This paper describes duration modeling in Text To Speech Synthesis (TTS) for Malayalam language using open source Festival TTS engine. Classification and Regression Tree (CART) based data-driven phoneme duration modeling is presented. A number of features are extracted for predicting the duration of phonemes. Objective evaluation test was conducted to evaluate the intelligibility of the synthesized speech by root mean squared error (RMSE) and correlation between actual and predicted durations. The objective evaluation of the model gave an RMSE of 0.1188 and a correlation of 0.9918.

show abstract

Duration modeling in a restricted-domain female-voice synthesis in Spanish using neural networks

Cited by 3 publications

References 6 publications

Selection of the most significant parameters for duration modelling in a Spanish text-to-speech system using neural networks

Selection of the most significant parameters for duration modelling in a Spanish text-to-speech system using neural networks

Phone duration modeling: overview of techniques and performance optimization via feature selection in the context of emotional speech

Duration modeling for text to speech synthesis system using festival speech engine developed for Malayalam language

Contact Info

Product

Resources

About