Fast, Accurate, Flexible Open Source Speech Recognition

Since being released as open source code in 1999, CMU Sphinx provides a platform for building speech recognition applications. It's used in desktop control software, telephony platforms, intelligent houses, computer-assisted language learning tools, information retrieval and mobile applications. Traditionally, CMUSphinx provides support for low-resource and underdeveloped languages.

lightbulb_outline View ideas list


  • c
  • cross-platform
  • hidden markov models
  • javascript
  • python


comment IRC Channel
email Mailing list
mail_outline Contact email

CMU Sphinx 2017 Projects

  • Yifan Xiong
    Collect Pronunciation Dictionaries from Wiktionary
    This Collect Pronunciation Dictionaries from Wiktionary project aims to expand pronunciation dictionaries in CMUSphinx for new words and multiple...
  • Pavel Denisov
    Diphone alignment and acoustic scores
    The goal of this project is to extend PocketSphinx so that it can calculate and provide alignments and acoustic scores for diphones similarly to how...
  • Muhammad Shah
    DNNs for Sphinx
    In the past decade Deep Neural Networks (DNNs) have been be demonstrated to excel to wide range of learning tasks, including speech recognition. More...
  • Sahith Dambekodi
    General Computer-Assisted Learning including Speaking Skills
    This proposal is for the implementation of Computer-Aided Language Learning from the browser using Pocketsphinx.js. Using Twee/Twine as the question...
  • Mritunjay Goutam
    Javascript simulation of the brain’s motor control of vocal tract-GSoC 2017 proposal
    As mention in the title, it is a 3D animation model of the motor control of speech production. Our long range goal is to implement the model...
  • Vishal Agrawal
    Large Vocabulary Continuous Speech Recognition using RNNs
    Automatic speech recognition systems are traditionally based on Hidden Markov models(HMMs) as it had given the best results in the past. However due...
    Leaderboard Population, Sorting, and Column Maintenance
    The project scope includes designing a web based leader board module for CMU Sphinx which would include details of top ranking people, models,...
  • Hammad Abdullah
    MLP incorporation in Sphinx
    CMUsphinx is a fast and flexible open source speech recognition toolkit. Currently it uses GMM acoustic models and it gives reasonable accuracy. This...
  • Brij
    Pronunciation Intelligibility Remediation with Pocketsphinx.js
    The proposed framework will implement a user interface capable of collecting audio signal from microphone corresponding to a prompted text and...
  • Pankaj Baranwal
    ROS Integration for pocketsphinx
    ROS has support for pocketsphinx, but it is very initial stage. So, this project aims to update the ROS package for pocketsphinx with a full-scale...
  • Rishi Rajasekaran
    Transcriber Qualification
    The aim of this project is to write support code for obtaining accurate transcriptions, exemplar pronunciations, and phonetic and part-of-speech...