Software Engineer, Speech
VoiceBox builds advanced speech applications that are used by millions of users. As a Speech Engineer you will have the opportunity to work on projects related to ASR and TTS integration, Statistical Language Modeling, Speech Recognition performance analysis, advanced conversational HMI, and Natural Language Understanding algorithms. We are looking for individuals who are passionate about speech interfaces and want to work on cutting edge technology while solving challenging problems.
- Maintain and enhance current integration of speech technologies such as Automatic Speech Recognition (ASR) and Text-To-Speech (TTS). This role requires a deep understanding of speech technologies, its terminology and its dependencies.
- Design and develop abstracted interfaces for different ASR systems, publicly and commercially available to facilitate their integration into VoiceBox's platforms. This role requires not only strong skills in speech technologies but also strong skills in software engineering.
- Facilitate grammar development for multiple languages, in particular US English, European Languages and Asian Languages (BNF, SRGS and SLM)
- Create complex test suites for rapid evaluation of speech recognition performance (Accuracy, Memory, Latency) and summarize results in written form
- Design and implement technologies in (especially spoken) human-machine interfaces, machine learning, probabilistic and symbolic reasoning to advance VoiceBox's Natural Language Understanding
- Assist with many aspects of the research & development including conversational modeling; running experiments, working with interactive Windows-based software for experiment control, signal processing, and data analysis; and performing graphical and statistical analysis of extracted data.
- BS or MS in Computer Science/Engineering or equivalent work experience (PHD is a plus)
- 5+ years relevant industry experience
- Extensive experience in C++ and other object oriented languages such as C# or Java. Experience with Bash, Perl or Python are a plus.
- Demonstrated knowledge of speech technology concepts, such as acoustics models, phonetics, and grammars
- Expert knowledge of context free grammars and statistical language models
- Solid understanding of databases and data analysis.
- Experience with cross-platform development, natural language processing, artificial intelligence, machine learning, signal processing, and statistical analysis are a plus
- Good problem solving, analytic skills and troubleshooting skills.
- Self motivated with the ability to work independently