1 / 12

ALPHABET RECOGNITION USING SPHINX-4

ALPHABET RECOGNITION USING SPHINX-4. BY TUSHAR PATEL . OUT LINE. WHY SPHINX-4? WHAT IS SPHINX -4 ? FRAME WORK IN SPHINX-4. PROJECT DEMO. CHANGES IN DEMO TO MAKE MY PROJECT. WHY IT IS OPEN SOURCE FRAME WORK?. WHY SPHINX-4?.

odin
Télécharger la présentation

ALPHABET RECOGNITION USING SPHINX-4

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. ALPHABET RECOGNITION USING SPHINX-4 BY TUSHAR PATEL

  2. OUT LINE • WHY SPHINX-4? • WHAT IS SPHINX -4 ? • FRAME WORK IN SPHINX-4. • PROJECT DEMO. • CHANGES IN DEMO TO MAKE MY PROJECT. • WHY IT IS OPEN SOURCE FRAME WORK?

  3. WHY SPHINX-4? • The traditional approach of speech recognition system design which is optimized a particular methodology. • In Past, researcher need to develop whole system for only one simple change in research. • Single approach • License requirement agreement • Sphinx-4 -Open source of frame work

  4. SPHINX-4 • Sphinx-4 is a modular and pluggable framework that uses design patterns from existing systems, with sufficient flexibility to support emerging areas of research interest. • Modular: - It Includes separable components of specific tasks. • Pluggable: - You can easily replace modules at run time

  5. FRAME WORK IN SPHINX-4 • Front end: -Takes one or more input signals and parameterizes them into a sequence of Features. • Decoder: -Translate any type of language model from pronunciation information from the dictionary and structural information from one or more sets of Acoustic Models, into a Search-Graph. • Decoder takes input from the front-end and search graph from the linguist for decoding and generate results.

  6. FRAME WORK • Linguist: -It is used to generate a search-Graph which is useful for decoder for search as well as hiding the complexities generated at the time of generation of graph. • Language model • Dictionary • Acoustic model

  7. ALPHABET RECOGNITION • This is a project in which I used the open source frame work of sphinx-4. • By making some changes in the given demo file, I have created my own project of Alphabet Recognition. • The recognizer is alphabet-recognizer and recognizes alphabets.

  8. DEMO OF PROJECT

  9. CHANGES IN DEMO FILE • JAVA FILE • GRAMMER FILE • CONFIGURATION FILE

  10. HOW YOU CAN CREAT YOUR OWN PROJECT? • It is easier to create your project by using open source of frame work of sphinx-4. • Linguist Frame: - By allowing different implementations of the Linguist to be plugged in at run time, Sphinx-4 also allows individuals to provide different configurations for different system and recognition requirements.

  11. Thank You

  12. Questions???

More Related