Difference between revisions of "VT Speech processing"
Line 47: | Line 47: | ||
VTP_Resources = | VTP_Resources = | ||
*[[SPEED task details | Project SPEED task details]] | *[[SPEED task details | Project SPEED task details]] | ||
}} | }} |
Revision as of 16:13, 9 February 2012
General Project Information
- Leader: Ing. Milan Rusko <milan.rusko@savba.sk>, IISAS, Slovakia (Administration: Gergely Sipos <gergely.sipos@egi.eu>)
- Mailing List: <to be setup>
- Status: Initiated
- Start Date: 01/02/2011
- End Date: not yet
- Meetings: not yet
Motivation
Current automatic speech processing technology is strongly oriented to data-driven approaches demanding huge computational power especially in the training and testing phases. The evaluation of an automatic speech recognition (ASR) system with one setting typically requires several hours of computing on a one hundred core computer cluster. Since there are tens of parameters and settings, most of the iteration based optimization seem to be too computationally expensive. Moreover, optimization of one part of the recognizer is not independent from the settings of the other parts. Speech processing community should therefore take the opportunity of exploiting the benefits of grid technology and its enormous computing power in an effort to achieve satisfactory optimization of the contemporary ASR systems. Furthermore, approaches useful for ASR can be easily extended to modern speech synthesis systems since both problems are commonly based on very similar principles of modeling.
Output
The expected output is two-fold. First, through a dedicated user-interface, Grid computing will become available to a wide scientific community of researchers dealing with speech processing. Second, a set of methods for optimization and diagnostics specifically in speech processing and tools implementing these methods in the grid platform will be developed.
Tasks
The required output for the project will be achieved by the following tasks:
- Establishment of contacts, investigation of the state of the art, formation of a consortium
- Methodology development for
- holistic optimization
- ASR (may include speaker identification, speaker recognition and language recognition)
- Text to Speech (TTS) systems
- holistic diagnostics
- ASR
- TTS
- holistic optimization
- Implementation aspects
- porting the computations in the Automatic Speech Processing domain to the Grid platform
- solving particular domain-dependent problems of using Grid computing in automatic speech processing
- Problem of needed high data transfers and its influence on Grid computing speed
- Data security and program security
- Storage possibilities for large databases in Grid
- Porting commercial applications to Grid
Members
- NGIs - confirmed:
- Slovakia:
- Ing. Milan Rusko (Institute of Informatics of the Slovak Academy of Sciences (Leader))
- Speech processing group
- Grid computing group
- Technical University in Košice, Slovak Republic
- Ing. Milan Rusko (Institute of Informatics of the Slovak Academy of Sciences (Leader))
- Slovakia:
- EGI.eu:
- Gergely Sipos