Speech Recognition Expert

German Autolabs makes driving safer and smarter. How we do it? By building a unique intelligent driving assistant in the connected car space.

As a Speech Recognition Expert, you will be responsible for automatic speech recognition for large vocabulary systems. You will be working with a cross-functional team of NLP specialists, developers, designers and product managers to develop an amazing product!

• Program primarily in C++, including software engineering, algorithms and API design
• Create a corpus of speech data for acoustic language models
• Actively develop enhancements to acoustic modeling mechanisms
• Identify, solve, and test bottlenecks in accuracy and performance of speech recognition system
• Improve performance of language models and decoder algorithms
• Convey detailed documentation of all designs and procedures

• Extensive background in statistical, speech algorithms, HMM, GMM, FST, acoustic modeling and advanced machine learning techniques
• Experience and knowledge in mainstream speech recognition softwares, DSP theory, feature extraction
• Experience in Language Modeling, e.g. Grammar based and  Statistical Language Modeling(SLMs)
• Familiarity with Kaldi ASR or Pocketsphinx
• Solid programming experience in C/C++,
• Able to solve real–world problems using cutting–edge ideas and independent research

‍

• An agile team of energetic, entrepreneurial and smart colleagues
• The opportunity to learn from interdisciplinary team of experts
• Exposure and insights into one of the most promising emerging tech ecosystems - the connected car
• A desk in the heart of Berlin, Europe's startup capital
• Team events & fun