[Elsnet-list] Speech Technology Research Engineer position at Speech Graphics

Gregor Hofer hofer at speech-graphics.com
Wed Nov 7 15:38:06 CET 2012

Speech Technology Research Engineer

About Speech Graphics


Speech Graphics is a fast-growing tech company based in Edinburgh,
Scotland, that has developed the first high-fidelity lip-sync solution
driven by audio. Based on two decades of research and development in
articulatory dynamics, facial modeling, speech recognition and
computer graphics, our award-winning technology is now helping us to
become the leading high-quality lip sync and facial animation provider
for next-gen games, as well as a spectrum of other developing
applications. Our clients include many AAA video game studios as well
as language instruction and speech therapy companies. We are a highly
interdisciplinary team that seeks talented, driven individuals from
various fields. We offer an exciting startup environment where
individuals can have a major impact on the direction of the company
and have a share in its success.

Job Description

We are looking for a creative, talented, motivated individual with an
appetite for problem solving to optimize the speech analysis
components in our audio-driven facial animation system, and produce
new research leading to further advances in audio-driven animation.


- Build and deliver acoustic models for various languages.
- Investigate training and decoding strategies to optimize performance
of speech recognition and related analyses.
- Investigate and implement pre- and post-processing steps to improve
output accuracy.
- Propose, research and develop new strategies for phonetic analysis
from acoustics including real-time methodologies.
- Produce clear documentation and research reports


- University degree in speech technology, computer science, or
electrical engineering; PhD in a relevant field and/or 3 years work
experience is a plus.
- Should possess a combination of research and implementation skills,
including significant programming experience in languages    such as
C++ and Python.
- Machine learning and acoustic modelling background.
- Experience with ASR frameworks such as HTK is highly desirable.
- Proficiency in English.

How to apply

Send a CV and cover letter to jobs at speech-graphics.com

Dr. Gregor Hofer
Chief Executive Officer
Speech Graphics Ltd.
Appleton Tower, Level 6
11 Crichton Street
Edinburgh EH8 9LE

Phone:  +44 (0) 131 668 6945
Mobile:  +44 (0) 78 677 66486
Twitter:  @speechgraphics
Web: www.speech-graphics.com

More information about the Elsnet-list mailing list