• Corpus ID: 16986951

FreeTTS: a performance case study

@inproceedings{Walker2002FreeTTSAP,
  title={FreeTTS: a performance case study},
  author={William Walker and Paul Lamere and Philip Kwok},
  year={2002}
}
The Java™ platform has a stigma of being a poor performer and has often been shunned as an environment for developing speech engines. We decided to better understand this stigma by writing a speech synthesis engine entirely in the Java programming language. Remarkably, we were able to get better performance from our engine than one using similar algorithms written in C. Our team, composed of three engineers with significant backgrounds in the C and Java programming languages, also found it… 
No Paper Link Available
32 Citations
Highly Influential Citations
2
Background Citations
7
Methods Citations
10

Figures and Tables from this paper

32 Citations

COMPARATIVE ANALYSIS OF JAVA AND C++ HISTORY, SIMILARITIES & DIFFERENCES, SYNTAX AND DESIGN ISSUES

This paper discuss about Java was initially created to support network computing on embedded systems . Java was designed to be extremely portable , secure , multi-threaded and distributed , none of…

Performance evaluation and prediction of open source speech engine on multicore processors

This paper quantifies the performance of the core part of voice driven web using free and open source speech engine; the speech engine which is very high computation demanding, it consists of…

ModelByVoice - towards a general purpose model editor for blind people

ModelByVoice is the base for a new tool that will enable MDD highlighting the relevant human factor of accessibility via voice and audio to models the same way it is already done with diagrammatic languages with the current Modelling workbenches.

THE CONSTRUCTION OF A PUN GENERATOR FOR LANGUAGE SKILLS DEVELOPMENT

The building and testing of the STANDUP program is described – a large-scale, robust, interactive, user-friendly pun-generator (inspired by Binsted's JAPE program), aimed at allowing children, particularly those with communication disabilities, to develop their linguistic skills.

VoiceToModel: an approach to generate requirements models from speech recognition mechanisms

The VoiceToModel framework is proposed to improve the accessibility of the requirements process by effectively integrating a requirements engineer or stakeholder with disabilities during requirements modelling.

Optimized Approach to Voice Translation

Techniques like template matching, indexing frequently used words using probability search and session-based cache can considerably enhance processing times, thereby increasing the throughput of voice translation services.

Text to Speech Synthesis for Bangla Language

This paper converted Bangla text to Romanized text based on Bangla graphemes set and by developing a bunch of romanization rules and an xml-based data representation is developed as a feature of the system.

Evaluation of Freely Available Speech Synthesis Voices for Halef

After conducting a subjective evaluation involving 36 participants, it is found that Festival was clearly outperformed by Mary and that unit selection voices performed en par, if not better, than HMM-based ones.

WikiSpeech - enabling open source text-to-speech for Wikipedia

We present WikiSpeech, an ambitious joint project aiming to (1) make open source text-to-speech available through Wikimedia Foundation’s server architecture; (2) utilize the large and active…

Segmentation Analysis using Synthetic Speech Signals

The adequateness of synthetic and natural corpora criteria for speech segmentation was proved and the experiments results showed that synthetic signals can be used for speech algorithm research.

References

SHOWING 1-10 OF 17 REFERENCES

The Java Virtual Machine Specification

This second edition specifies the newest version of the Java virtual machine and provides a fascinating view into the inner workings of theJava 2 platform.

Generating F/sub 0/ contours from ToBI labels using linear regression

  • A. BlackAndrew J. Hunt
  • Physics
    Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96
  • 1996
The method uses linear regression to predict F/sub 0/ target values for the start, mid-vowel and end of every syllable, using features representing the ToBI labels, stress and syllable position, with significant improvements on a previous rule driven method.

Generating F0 contours from toBI labels using linear regression

TOBI: a standard for labeling English prosody

Issues in high quality LPC analysis and synthesis

“ Building Voices in the Festival Speech Synthesis System Processes and issues in building speech synthesis voices Edition 1 . 2 : beta , for Festival version 1 . 4 . 1

  • 2000

The CMU Pronouncing Dictionary Version 0.6. Unpublished content available at http

  • The CMU Pronouncing Dictionary Version 0.6. Unpublished content available at http

Building Voices in the Festival Speech Synthesis System Processes and issues in building speech synthesis voices Edition

  • 2000

" The Festival Speech Synthesis System , Version 1 . 4 . 2

  • 2001

The Boston University Radio News Corpus.

  • Technical Report ECS-95-001,
  • 1995