Job Description Ford Motor Company is moving into a new phase of its 100+ year history, one in which openness is at the heart of its future. The automobile is being redefined as a networked computing platform upon which an ever-evolving set of applications is being designed, allowing us to create exciting new consumer experiences.
We are a research lab within Ford that is investigating advanced speech recognition and hands-free calling technologies. The candidate will be involved with developing expertise in programming the speech recognition engine used in Ford’s SYNC system. They will develop experimental capability to perform vehicle-specific speech engine parameter tuning to minimize recognition error rates. They will also develop similar capabilities to interface to cloud-based recognizers (e.g., Siri, Google Assistant, etc.) as a means of evaluating recognition accuracy. This work will be instrumental for development of hybrid embedded/cloud strategies for speech recognition. Vehicle factors such as background noise and cabin acoustics will also be quantified in relationship to speech recognition.
The ideal candidate will have exceptional programming skills in Matlab, Python, C and C++. Experience with speech processing and recognition systems would be a plus. The candidate should enjoy working in close-knit, collaborative environments. We are looking for exceptionally creative, motivated and talented computer science and electrical engineers to join our team. We collaborate extensively within Ford and with external partners, thus we require excellent communication and collaborative skills.
This position is located at Ford’s Research and Innovation Center in Dearborn, MI. Candidates will be considered who do not have a background in speech recognition but have some familiarity with machine learning techniques.
Responsibilities include:
Develop experimental capability to perform vehicle-specific speech interface design and Proof of Concepts (POCs)
Develop capabilities to interface to cloud-based recognizers
Help develop hybrid embedded/cloud-based speech recognition strategies
Perform experiments to understand vehicle effects (noise, cabin acoustics, etc.) on speech recognition
Support speech recognition technology development through the development of POCs
Minimum Qualifications:
Bachelor’s degree in Electrical Engineering or Computer Science
2 years Matlab, C, C++ background
1 year Experience with machine learning techniques
Preferred Qualifications:
Experience with speech recognition engines and natural language understanding/processing
Experience with speech processing and speech recognition techniques
Experience programming in Python
Strong record of intensive, collaborative projects
Desire to make an impact on product
Strong affinity for self-directed learning: if you don’t know something, you find out quickly
Exceptional verbal and written communication skills
The distance between imagination and … creation. It can be measured in years of innovation, or in moments of brilliance. When you join the Ford team discover all the benefits, rewards and development opportunities you’d expect from a diverse global leader. You’ll become part of a team that is already leading the way, with ingenious solutions and attainable products – and it is always ready to go further.
Visa sponsorship may be available for this position.
Ford Motor Company is an equal opportunity employer committed to a culturally diverse workforce. All qualified applicants will receive consideration for employment without regard to race, religion, color, age, sex, national origin, sexual orientation, gender identity, disability status or protected veteran status.