CMUSphinx4
Authors: | Evandro Gouvea, Peter Gorniak, Philip Kwok, Paul Lamere, Beth Logan, Pedro Moreno, Bhiksha Raj, Mosur Ravishankar, Bent Schmidt-Nielsen, Rita Singh, JM Van Thong, Willie Walker, Manfred Warmuth, Joe Woelfel, Peter Wolf |
---|---|
Updated: | Wed 23 October 2019 |
Source: | https://cmusphinx.github.io/ |
Type: | Java script |
Languages: | English, French, Mandarin, German, Dutch, Russian |
Keywords: | speech, programming, Java, experiment, English, French, Mandarin, German, Dutch, Russian |
Open Access: | yes |
License: | BSD-style |
Documentation: | https://cmusphinx.github.io/wiki/ |
Publications: | Lamere, P., Kwok, P., Gouv, E., Singh, R., Walker, W., Wolf, P. (2003). The CMU Sphinx4 Speech Recognition System. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2003). |
Citation: | CMUSphinx. (2019). Github. https://cmusphinx.github.io/ |
Summary: | The Sphinx-4 speech recognition system is the latest addition to Carnegie Mellon University's repository of Sphinx speech recognition systems. It has been jointly designed by Carnegie Mellon University, Sun Microsystems Laboratories and Mit- subishi Electric Research Laboratories. It is differently designed from the earlier Sphinx systems in terms of modularity, flexibility and algorithmic aspects. It uses newer search strategies, is universal in its acceptance of various kinds of grammars and language models, types of acoustic models and feature streams. Algorithmic innovations included in the system design enable it to incorporate multiple information sources in an elegant manner. The system is entirely developed on the JavaTM platform and is highly portable, flexible, and easier to use with multithreading. |