Senior Speech Technology Engineer at Uniphore
Chennai, IN
Experience: 2-8 years
Education: MS in Computer Science, Electrical Engineering, Applied Mathematics or equivalent field, or BS with equivalent R&D experience

Ability to handle multiple projects
Operating Systems - Windows & Linux. Languages: Java, Python
Familiarity with modern speech recognition engine technology. LVCSR, HMMs, DNNs
Familiarity and experience with speech recognition engines and open-source/commercial toolkits such as Google Speech, Sphinx, Nuance, Kaldi & IBM Watson
Knowledge of techniques for problem areas such as accuracy, noise, NBest, confidence scoring, keyword recognition
Should be at ease with both grammars and statistical language modeling. Experience tuning grammars and SLMs to boost recognition accuracy
Good experience with (and knowledge of) Statistical Signal Processing
Experience with speech processes (such as diarization and silence detection) involving computation with features extracted from acoustic signals
Knowledge of (and experience with) modern methods in machine learning, including Deep Learning methods
Experience with testing and evaluating speech processes systems
Familiarity with text-to-speech
Knowledge of (and experience with) phonology, phone sets, pronunciation dictionaries is a plus
Solid basics in statistics
Knowledge of (and experience with) NLP problems and techniques is a plus
Experience working with Indian languages (data collection, annotation, Romanization, ASR/TTS systems, NLP) is a plus
Keeping up with developments and progress in ASR, NLP and Machine Learning
Required Qualification

Functional Skills

Passion and commitment to work in a start-up environment