Job Description

Title: Speech Recognition Engine Software Developer (Contractor/Consultant)

GFT Group seeks a speech recognition engine software developer. Experience creating Microsoft SAPI compliant or compatible engines would be helpful. Experience implementing or modifying speech recognition engines and algorithms in C. or other compiled languages would be helpful. Experience with Sphinx or other open-source speech recognition engines may be helpful. Specific projects are discussed below.

GFT Group is developing a new speech recognition engine with superior accuracy compared to current speech recognition engines such as Dragon Naturally Speaking, ViaVoice, Microsoft Speech, and the open-source SPHINX speech recognition engine. The engine should enable or enhance rapid jumping to targets such as files, web sites, PowerPoint slides, submenu selections and so forth on computers by simple voice command, dictation of documents, and hands-free operation of computers, cell-phones, automobile accessories and many other devices. Our goal is to achieve 100% accurate speaker-independent phoneme recognition in the presence of typical background sounds such as car noises that do not impair human speech recognition. We do not expect to solve the homonym resolution problem for general unstructured human speech. The effective speech recognition accuracy, the word error rate, of the engine will be determined by the frequency of homonyms and near-homonyms, words and phrases that sometimes sound the same, in the recognized speech.

Projects

1. We are looking for a SAPI compliant or compatible wrapper for our speech
recognition engine. If you have code to do this or can do it quickly, we
would be interested in buying or licensing this.

2. The methods that we are developing would improve or replace a key component of the acoustic model in current speech recognition algorithms. The project would be to adapt a
standard speech-recognition engine such as Sphinx so that our methods could
be swapped in place of this key component.. The hidden Markov models would
have to be retrained or replaced with a different pattern classifier. If you or your organization has an alternative engine to
Sphinx, we would consider buying or licensing it.

3. In the longer run, we are looking for licensing representatives with
good business contacts to license the technology to appropriate customers
such as speech-recognition companies, communication companies, and so forth.
Obviously, this is not relevant until we have demonstrated a working
technology.

GFT Group is a private research and development and contracting
organization with several products in the speech recognition field.
For more information, see http://www.Petrana.net

Please submit a cover letter and a résumé and/or curriculum vitae in
the body of a single plain text e-mail message. Please send plain text only. No attachments, hypertext, or
active content. Please include the phrase "Speech Engine Software Developer" in e-mail
subject line. Please send to:

John F. McGowan, Ph.D.
President, Research and Development Division
GFT Group Inc.
jmcgowan@GFTGroup.com