Text to speech—An overview

Olive, Joseph P.; Liberman, Mark

doi:10.1121/1.2022951

Cited by 43 publications

(29 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar models were developed in other languages, such as: French (Bartkova and Sorin 1987), Swedish (Carlson and Granstrom 1986), German (Kohler 1988) and Greek (Epitropakis et al 1993), and varieties, such as: American English (Allen et al 1987;Olive and Liberman 1985) and Brazilian Portuguese (Simoes 1990). The major drawback of the rule-based approaches is the difficulty to represent and manually tune all the linguistic factors which influence the segmental duration in speech.…”

Section: Rule-based Techniquesmentioning

confidence: 89%

“…The phone duration modeling methods reported in the literature can be broadly divided in two major categories: the rule-based (Allen et al 1987;Bartkova and Sorin 1987;Carlson and Granstrom 1986;Epitropakis et al 1993;Klatt 1979;Olive and Liberman 1985;Simoes 1990) and the data-driven methods (Chien and Huang 2003;Goubanova and King 2008;Lazaridis et al 2007;Möbius and Santen 1996;Riley 1992;Takeda et al 1989). Although, in the present study we consider only duration modeling techniques, which belong to the category of datadriven methods, for comprehensiveness of exposition we briefly review also the main rule-based techniques.…”

Section: Overview Of Phone Duration Modeling Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Rule-based Techniquesmentioning

confidence: 89%

Section: Overview Of Phone Duration Modeling 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

show abstract

“…Initially a set of intrinsic (starting) values was assigned on each phone which was modified each time according to the extracted rules. Models of this type and similar to this were developed in many languages such as French (Bartkova and Sorin, 1987), Swedish (Carlson and Granstrom, 1986), German (Kohler, 1988) and Greek (Epitropakis et al, 1993;Yiourgalis and Kokkinakis, 1996), as well as in several dialects such as American English (Allen et al, 1987;Olive and Liberman, 1985) and Brazilian Portuguese (Simoes, 1990). The main disadvantage of the rule-based approaches is the difficulty to represent and tune manually all the linguistic factors, such as the phonetic, the morphological and the syntactic ones, which influence the segmental duration in speech.…”

Section: Introductionmentioning

confidence: 94%

Improving phone duration modelling using support vector regression fusion

Lazaridis

Mporas

Ganchev

et al. 2011

Speech Communication

View full text Add to dashboard Cite

In the present work, we propose a scheme for the fusion of different phone duration models, operating in parallel. Specifically, the predictions from a group of dissimilar and independent to each other individual duration models are fed to a machine learning algorithm, which reconciles and fuses the outputs of the individual models, yielding more precise phone duration predictions. The performance of the individual duration models and of the proposed fusion scheme is evaluated on the AmericanEnglish KED TIMIT and on the Greek WCL-1 databases. On both databases, the SVR-based individual model demonstrates the lowest error rate. When compared to the second-best individual algorithm, a relative reduction of the mean absolute error (MAE) and the root mean square error (RMSE) by 5.5% and 3.7% on KED TIMIT, and 6.8% and 3.7% on WCL-1 is achieved. At the fusion stage, we evaluate the performance of twelve fusion techniques. The proposed fusion scheme, when implemented with SVR-based fusion, contributes to the improvement of the phone duration prediction accuracy over the one of the best individual model, by 1.9% and 2.0% in terms of relative reduction of the MAE and RMSE on KED TIMIT, and by 2.6% and 1.8% on the WCL-1 database.

show abstract

“…Starting from some intrinsic value, the duration of a segment is modified by successively applied rules. Models of this type have been developed for several languages including American English [1,13], Swedish [4], German [9], French [2], and Brazilian Portuguese [17]. When large speech databases and the computational means for analyzing these corpora became available, new approaches were proposed based on, for example, Classification and Regression Trees (CART) [14,15] and neural networks [3].…”

Section: Introductionmentioning

confidence: 99%

Modeling segmental duration in German text-to-speech synthesis

Möbius¹,

Santen²

Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96

View full text Add to dashboard Cite

This paper reports on the construction of a model for segmental duration in German. The model predicts the durations of speech sounds in various textual, prosodic, and segmental contexts. It has been implemented in the German version of the Bell Labs text-tospeech system [18,12]. The construction of the duration system was made efficient by the use of an interactive statistical analysis package that incorporates the approach outlined in [23]. The results are stored in tables in a format that can be directly interpreted by the TTS duration module. Tables are constructed in two phases: inferential-statistical analysis of the speech corpus, and parameter estimation. The overall correlation between observed and predicted segmental durations is .896.

show abstract

Text to speech—An overview

Cited by 43 publications

References 0 publications

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

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

Improving phone duration modelling using support vector regression fusion

Modeling segmental duration in German text-to-speech synthesis

Contact Info

Product

Resources

About