Voxedu aims to revolutionize online language-learning by providing fun, speech-based content via a powerful distribution platform.
We are developing a proprietary cloud-based platform that utilizes telephony and mobile data services to power and distribute interactive speech recognition content for language-learning applications.
VoxEdu is an early-stage edutech startup in the Bay area currently operating in seed funding mode. We are passionate about making language learning accessible to everyone through fun, social and most importantly, speech-based interaction and learning on mobile devices.
Our solution is an interactive speech-based engine that powers real-time language curriculum and pronunciation feedback. In tandem with a team of expert language specialists developing core curriculum, we believe we can literally re-shape the conversation around what language proficiency means to consumers across the globe.
Development of common libraries/interface for both pronunciation and generic language recognition.
Development of reliable feedback mechanism for pronunciation provided through sound files given by an end user on a mobile device
Work with the VP eng to integrate the speech recognition engine into the VoxEdu application platform.
Some experience preferred in research, development and optimization of speech recognition engines.
Some experience in building interactive systems with speech engines.
Experience in training speech recognition engines in different language learning such as English, French, Spanish, Mandarin etc.
Speech and voice recognition work, either in an academic or start-up environment.
Ability to lead the development of algorithms and machine learning to enhance VoxEdu's prototypes.
Masters/PhD degree in Electrical Engineering/Computer Science with speech recognition major.
Co-Founder and Salary upon funding.