190 Hits in 3.2 sec

Speech timing in Slovenian TTS

Jerneja Gros, Nikola Pavesic, France Mihelic
1997 5th European Conference on Speech Communication and Technology (Eurospeech 1997)   unpublished
Speech timing at different speaking rates was studied for the Slovenian language and the results were applied for duration modelling in the Slovenian text-to-speech system S5 [1] .  ...  phoneme groups for the Slovenian language [2].  ...  PERCEPTUAL EVALUATION The adequacy of the TTS system was tested in terms of acceptability and in terms of intelligibility.  ... 
doi:10.21437/eurospeech.1997-129 fatcat:oqvp443smzdi7i62xa4sfevtty

A Text-To-Speech System For The Slovenian Language

J. Gros, F. Mihelic, N. Pavesic
1996 Zenodo  
Publication in the conference proceedings of EUSIPCO, Trieste, Italy, 1996  ...  A text-to-speech (TTS) system, capable of synthesising continuous Slovenian speech from an arbitrary input text is described.  ...  For the Slovenian language, several attempts were made in the past, where different aspects of a Slovenian TTS system were covered [1, 2, 3] .  ... 
doi:10.5281/zenodo.36331 fatcat:2tfffb7735grfdhxgrb4smrupm

Slovenian Text-To-Speech Synthesis For Speech User Interfaces

Jerneja Žganec Gros, Aleš Mihelič, Nikola Pavešić, Mario Žganec, Stanislav Gruden
2007 Zenodo  
The paper presents the design concept of a unitselection text-to-speech synthesis system for the Slovenian language.  ...  Since memory and processing power requirements are important factors for a possible implementation in embedded devices, lexica and speech corpora need to be reduced.  ...  We encourage other groups working on Slovenian TTS to use the same reference speech when evaluating their TTS systems.  ... 
doi:10.5281/zenodo.1055796 fatcat:5kvjmpm5rbdulkwmmuvq7bh3ky

Homer II—man–machine interface to internet for blind and visually impaired people

Nikola Pavešić, Jerneja Gros, Simon Dobrišek, France Mihelič
2003 Computer Communications  
HOMER II is a voice-driven text-to-speech system developed for blind or visually impaired persons for reading Slovenian texts.  ...  The output interface performs speech synthesis of a given text and in addition prints the same text magnified to the screen.  ...  Acknowledgements This work was partly supported with Grant No. 3411-00-22 2109 from the Slovenian Ministry of Science and Technology (MZT) and Association of Slovenian Blind and Visually Impaired Persons  ... 
doi:10.1016/s0140-3664(02)00164-0 fatcat:blmyvhcyzvg2zhusbz6yyq5btq

Adapting Prosody in a Text-to-Speech System [chapter]

Janez Stergar, Caglayan Erdem
2010 Products and Services; from R&D to Final Solutions  
Adapting Prosody in a Text-to-Speech System 333 parameters given by sound duration and intonation contours enables a TTS backend to produce natural-sounding, high quality, synthetic speech (Edgington et  ...  The database construction The first step towards a data driven learning process is the design of speech corpora suitable for (in our case concatenative) TTS synthesis.  ...  Conclusion In the foregoing sections we introduced the adaptation of a multilingual TTS system to Slovenian language.  ... 
doi:10.5772/10398 fatcat:ijc4hpifmfetdn74hk52lepx2q

Time and space-efficient architecture for a corpus-based text-to-speech synthesis system

Matej Rojc, Zdravko Kačič
2007 Speech Communication  
This paper proposes a time and space efficient architecture for a multilingual text-to-speech synthesis system (TTS).  ...  The proposed architecture was successfully used when implementing the Slovenian PLATTOS corpus-based TTS system, as presented in this paper.  ...  The PLATTOS TTS system is a corpus-based speech synthesis system for the Slovenian language, using a concatenative approach and TD-PSOLA speech synthesis algorithm.  ... 
doi:10.1016/j.specom.2007.01.007 fatcat:2hci2tm275emfjogdraoyglkla

Multilingual and Multimodal Corpus-Based Text-to-Speech System - PLATTOS - [chapter]

Matej Rojc, Izidor Mlakar
2011 Speech and Language Technologies  
Slovenian implementation of the multilingual and multimodal corpus-based PLATTOS TTS system is presented in Section 5.  ...  The time and space-efficient architecture of the corpusbased TTS system is presented in Section 2. The unit selection process for corpus-based TTS systems is then described in Section 3.  ...  However, speech technology-based applications demand time and space-efficient multilingual, polyglot, and multimodal TTS systems.  ... 
doi:10.5772/16245 fatcat:ga3vmxvvevcx3a4352oehbwcky

The Wizard of Oz System for Weather Information Retrieval [chapter]

Melita Hajdinjak, France Mihelič
2003 Lecture Notes in Computer Science  
Data for speech recognition, speech understanding and construction of the dialogue manager is being collected with a Wizard-of-Oz (WOZ) system.  ...  The WOZ simulation results are presented and a brief description of our spontaneous speech database is given. . . .  ...  Acknowledgments We would like to thank the Environmental Agency of the Republic of Slovenia for kindly allowing us to use their weather data in our WOZ experiments.  ... 
doi:10.1007/978-3-540-39398-6_57 fatcat:rm6qeiihj5fltk6aq4qvkwdwrm

The reception of Canadian literature in Slovenian translations till 1980

Julijana Mary Dolenšek Vode
1998 Acta Neophilologica  
Slovenian reader.  ...  The primary questions were: how many Canadian authors writing in English were translated into Slovenian, how far back do these translations go, who were the translators and what was the influence on the  ...  Jack London introduced to the Slovenian reader the strong individual and true comrade. He showed that in this country there is only time to think how to survive.  ... 
doi:10.4312/an.31.1.123-127 fatcat:uxnony7u6bhqfk6vfyiljpsble

TTS-Driven Synthetic Behaviour-Generation Model for Artificial Bodies

Izidor Mlakar, Zdravko Kačič, Matej Rojc
2013 International Journal of Advanced Robotic Systems  
The system is TTS-driven and fused with the time-andspace efficient TTS-engine, called 'PLATTOS'.  ...  Visual perception, speech perception and the understanding of perceived information are linked through complex mental processes.  ...  The complete system synthesized speech output in the Slovenian language by using the TTS PLATTOS engine.  ... 
doi:10.5772/56870 fatcat:ke7ci7srvnhnrgok62mtxsaxvi

A Survey :On Text To Speech Synthesis

Ramita P. Karpe
2018 International Journal for Research in Applied Science and Engineering Technology  
Text-to-speech (TTS) synthesizer converts an input text into speech waveforms. It has been an effective tool for many visually challenged people for reading through hearing feedback.  ...  There has been a significant improvement in the research related to the development of the TTS system in Indian Languages in the past few years.  ...  LP and TD-PSOLA Based Incorporation of Happiness in Neutral Speech Using Time Domain [22] Sreenidhi S, et al.  ... 
doi:10.22214/ijraset.2018.3054 fatcat:cmobtkhnuvb7dpcx7kv6nhmwwu

An Efficient Unit-selection Method for Concatenative Text-to-speech Synthesis Systems

Jerneja Zganec Gros, Mario Zganec
2008 Journal of Computing and Information Technology  
This paper presents a method for selecting speech units for polyphone concatenative speech synthesis, in which the simplification of procedures for search paths in a graph has accelerated the speed of  ...  Due to its low processing power and memory footprint requirements, the method is suitable for use in embedded speech synthesizers.  ...  The time required to calculate the optimal path increases almost linearly with the increase in the size of the speech corpus.  ... 
doi:10.2498/cit.1001049 fatcat:f2xedo5ttvf3vd46y37i2zw4aa

Verbal Aspect in Correlation with Other Verbal Categories in the 16th-Century Slovenian Literary Language

2006 Slavistična Revija  
(aspect as point of departure, and time, voice, and mood) in the 16th-century Slovenian literary language.  ...  1 On the relationship between the suffixes -ova-in -ava-, which present one of the most noticeable derivational alternations in the language of the Slovenian 16 th -century Protestant writers, cf.  ...  The verb introducing direct speech is in Trubar's language commonly expressed with the historical present.  ... 
doaj:9feeddf9283d4712a67cfd2f586ef755 fatcat:im7oomjtujgzfcqvnkgbm2bvzy

MAKEDONKA: Applied Deep Learning Model for Text-to-Speech Synthesis in Macedonian Language

Kostadin Mishev, Aleksandra Karovska Ristovska, Dimitar Trajanov, Tome Eftimov, Monika Simjanoska
2020 Applied Sciences  
We created a dataset that contains approximately 20 h of speech from a native Macedonian female speaker, and we use it to train the text-to-speech (TTS) model.  ...  The achieved MOS score of 3.93 makes our model appropriate for application in any kind of software that needs text-to-speech service in the Macedonian language.  ...  Acknowledgments: The work was inspired by Erasmus+ KA203 FAST: Fostering Accessible Study Technologies-Accessible Learning Management System in Humanities and Social Sciences (project reference: 2018-1  ... 
doi:10.3390/app10196882 fatcat:7ysb22hdobbr5o4svxyj3us6yu

Multilingual Conversational Systems to Drive the Collection of PROs and Integration into Clinical Workflow

Daniel Hari, Valentino Šafran, Umut Arioz, Izidor Mlakar, Matej Rojc, Gazihan Alankus, Rafael Perez Luna
2021 WSEAS Transactions on Biology and Biomedicine  
As a result, chatbots and 3D embodied conversational agents (ECA) were prepared to interact with the cancer patients in 5 different languages.  ...  Collection of patient-reported outcomes (PROs) remotely and their usage in the clinical workflow provide an improvement on both patient's quality of life and cancer care.  ...  Four microservices are used in this study. The first microservice is Speech synthesis, Text-to-speech (TTS) microservice.  ... 
doi:10.37394/23208.2021.18.13 fatcat:rk3ii7gaqvhwzeh2hoqo3zhc6a
« Previous Showing results 1 — 15 out of 190 results