We are the Speech Recognition team of AICS. AICS is a newly formed software division with a start-up vibe, innovation, and sound growth mindset. We focus on providing SaaS and AI solutions for enterprises to solve the real problems for various industries. Our team is looking for a passionate, talented engineer with a strong machine learning and speech background to help build industry-level speech technology on our products.
Responsibilities:
Your responsibilities may involve one or more of the following tasks:
Train and test speech recognition models (acoustic and language) using the latest methods.
Develop speech recognition software to integrate acoustic and language models into a real-time system.
Design and implement robust acoustic modeling algorithms for adverse acoustic conditions, such as far-field, reverberant, and noisy environments.
Design and conduct experiments to find methods to improve speech recognition accuracy.
Understand speech processing, acoustic modeling, language modeling, speech recognition, speech denoising, and speech enhancement.
Qualifications:
Strong machine learning background and familiar with the latest techniques applied to speech.
Excellent communication and teamwork skills.
Strong analytical and problem-solving skills.
Experience with Kaldi and/or ML framework.
C/C++, Python coding skills.
Degree in computer science, electrical engineering or related fields.