14
#SummitNow Yes, I'm able to index audio files within Alfresco 2013 Fernando González [email protected] @fegorama

AAT Module for Alfresco at Summit 2013

Embed Size (px)

DESCRIPTION

Presentation of Module for Alfresco AAT (Alfresco Audio Transcriber) at Summit 2013

Citation preview

Page 1: AAT Module for Alfresco at Summit 2013

#SummitNow

Yes, I'm able to index audio files within Alfresco

2013Fernando González

[email protected]@fegorama

Page 2: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

Why?

• A lot of audio/video files in many companies

• The need to seek words in audio files

• Transcription of important conversations

• Efficiency in DAM

[email protected]@fegorama

Page 3: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

AAT (Alfresco Audio Transcriber)

Alfresco Action (Java) for audio transcription with Sphinx-4 from

Carnegie Mellon University

What is it?

[email protected]@fegorama

Page 4: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

A group of speech recognition systems developed at Carnegie Mellon University.

These include a series of speech recognizers (Sphinx 2 - 4) and an acoustic

model trainer (SphinxTrain).

What is Sphinx-4?

[email protected]@fegorama

Page 5: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

Language model:GrammarsDictionaries

Acoustic models:Hidden Markov Model (HMM)

Elements of Sphinx-4

[email protected]@fegorama

Page 6: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

How does the action work?The action…

•Transcribes by direct execution

•Transcribes using content rules

•Transcribes using UI-Actions

•Transcribes with Alfresco Scheduler

[email protected]@fegorama

Page 7: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

Features • Use of Sphinx-4 and JSAPI2 for recognition

• Use of "policies" to transcribe uploaded content• Use of "scheduler" to transcribe spaces

programmatically• Use of action “Audio Transcriber" in user

interfaces (Alfresco Explorer and Share)• List of available Audio Files• Assignment of "aspects" to control

transcriptions

[email protected]@fegorama

Page 8: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

Architecture

• Alfresco API (Actions)

• Share API (UI-Actions)

• JSAPI2

• Sphinx-4 API

[email protected]@fegorama

Page 9: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

Transcriber Action

• Upload the file (WAV,…)

• Run the Action

• Call to transcriber and recognizer

• Capture words and other properties

• Indexing…

Page 10: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

Model for audio-indexingAspect: Transcriber

Property: WordsIndex: Atomic and Tokenized

Property: FramesIndex: No

Words and Frames are multiple

Page 11: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

Ways to transcribe

• Automatic transcription• Upload/Create and Load documents• Actions/Rules

• Programming transcription• Scheduled Actions

• Interactive transcription• Repository action running• UI Action running

Page 12: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

Fields of application

DAM (Digital Asset Management)

Trials recording

Movies and Songs

Radio and TV

Education

Page 13: AAT Module for Alfresco at Summit 2013

#SummitNow

#SummitNow

To Do…New formats of audio files for transcriptions

Internationalization (Grammars and Acoustic models)

Specialized Dictionaries

Refactoring, refactoring and refactoring…

Page 14: AAT Module for Alfresco at Summit 2013

#SummitNow