Senior Software Engineer - Audio (675080)
Apply NowCompany: Netpace
Location: Cambridge, MA 02139
Description:
Description:Job Description - Audio Software Engineer
Cambridge, MA
Our project is developing a new class of robotic platforms for social interaction. Your role is a mixture of applied research and production development of interactive audio technologies for innovative new products. These technologies span speech processing, music technology, multimodal vision and acoustic sensor fusion, and hardware design. The ideal candidate should be passionate about applying audio technologies to create engaging new user experiences on physical robots. You will work collaboratively within a global effort that includes locations in Silicon Valley, Boston, Shenzhen, Beijing, and Nanjing.
Job Responsibilities
Develop speech processing algorithms, e.g. voice activity, vocal affect, laughter detection
Research, evaluate, and integrate off-the-shelf solutions for required audio modules, e.g. sound localization, hot-word detection, speech recognition
Manage data collection for data-driven audio processing approaches
Evaluate state of the art audio hardware such as microphone arrays, speakers, and DSP chips
Develop multimodal perception approaches fusing audio and vision
Prototype innovative applications of spoken and musical interaction for social robotics
Collaborate with software team on system architecture design for audio processing pipeline
Collaborate with hardware team on design and integration of audio hardware components
Write documentation and tests for implemented modules
Requirements for position:
MS or PhD in Electrical Engineering, Computer Science, Music Technology, or related field
Experience with real-time digital signal processing
Experience with human speech processing
Experience with developing end-to-end interactive systems
Java, C++, Python language skills
Experience with Android OS and application development
Creativity and passion to bring new ideas to the table as well as drive them to completion
Work authorization in the US
Willingness to travel internationally and work across time zones
Cambridge, MA
Our project is developing a new class of robotic platforms for social interaction. Your role is a mixture of applied research and production development of interactive audio technologies for innovative new products. These technologies span speech processing, music technology, multimodal vision and acoustic sensor fusion, and hardware design. The ideal candidate should be passionate about applying audio technologies to create engaging new user experiences on physical robots. You will work collaboratively within a global effort that includes locations in Silicon Valley, Boston, Shenzhen, Beijing, and Nanjing.
Job Responsibilities
Develop speech processing algorithms, e.g. voice activity, vocal affect, laughter detection
Research, evaluate, and integrate off-the-shelf solutions for required audio modules, e.g. sound localization, hot-word detection, speech recognition
Manage data collection for data-driven audio processing approaches
Evaluate state of the art audio hardware such as microphone arrays, speakers, and DSP chips
Develop multimodal perception approaches fusing audio and vision
Prototype innovative applications of spoken and musical interaction for social robotics
Collaborate with software team on system architecture design for audio processing pipeline
Collaborate with hardware team on design and integration of audio hardware components
Write documentation and tests for implemented modules
Requirements for position:
MS or PhD in Electrical Engineering, Computer Science, Music Technology, or related field
Experience with real-time digital signal processing
Experience with human speech processing
Experience with developing end-to-end interactive systems
Java, C++, Python language skills
Experience with Android OS and application development
Creativity and passion to bring new ideas to the table as well as drive them to completion
Work authorization in the US
Willingness to travel internationally and work across time zones