Skip to main content

Posts

Featured

GSoC 2017 comes to a close

This year's GSoC is ending now, so this will be my last blog for the journey I went through with my teammates and mentors. Working with cmusphinx has been an amazing experience and a constructive way ahead in my basic understanding of speech research.  James Salsman conceived the idea of creating an authentic pronunciation intelligibility remediation framework using pocketsphinx.js. We started working on it since the start of this summer, enhanced pocketsphinx.js to extract pronunciation specific features, used DNNs to predict intelligibility score and finally came up with the framework which can be integrated with Wiktionary's native interface to open this functionality to all the users. Details of the final product and a live demo is up at this link:  DEMO Here's how the new interface would look on Wiktionary. We integrated this repository with pocketsphinx.js  which will enable it to accept recorded audio in proper format and extract pronunciation

Latest posts

Week 12: Frozen code and Wiktionary updates pending

Week 11: Starting to put stuff together

Week 10: Resolved blocker bugs from pocketsphinx.js and updating feature extraction

Week 9: Debugging Emscripten compiled pocketsphinx.js with new alignment features

Week 8: Generic feature extraction frontend in Wiktionary and Alignment API in pocketsphinx.js

Week 7: Wiktionary code re-structuring and new fast feature extraction

Week 6: New features for pronunciation and Improved audiorecorder.js

Week 5: Recorder interface on Wiktionary

Week 4: Data from mechanical turk and Wiktionary interface

Week 3: Experiments with DNNs and Logistic Regression