Ever dreamed of being a rock star, or becoming the voice of your smart device? Well now you can, using ObEN’s speech-to-singing and text-to-speech (TTS) personalization technology. Beyond the power of speech, ObEN continually strives forward until it realizes the ’Virtual Me’, your complete virtual identity that combines your voice with your appearance in virtual reality (VR). Meet us at Interspeech to get a sneak peak of ObEN’s proprietary artificial intelligence (AI) technology.

We will be exhibiting in San Francisco from September 9 -12 at Interspeech 2016, the largest conference for speech and communication technologies of the year. With ObEN as a fellow exhibitor, Interspeech 2016 displays a wide variety of speech theory and applications, with this year’s topic centered around understanding speech processing in humans and machines.

ObEN’s technology aspires to create the ‘Virtual Me’ which is composed of your personalized 3D photo-real virtual avatar, digital voice, and AI. At Interspeech 2016, ObEN will showcase its technology in creating the virtual avatar and digital voice. Interspeech 2016 attendees can immerse themselves in the experience using a smartphone photo and reading lyrics to develop their personalized ‘Virtual Me’, complete with their personalized digital voices. It took Team ObEN’s efforts working in speech analysis and synthesis, a 3D visual development process, and deep learning algorithms to create the ‘Virtual Me’—all three as proprietary technology developed in-house at ObEN’s headquarters in Pasadena, CA.

ObEN’s speech-to-singing and TTS Personalization enables limitless possibilities. One such possibility is have you sing a full solo or duet with a singer just by reading the lyrics! You can also choose to have personal assistants sound like your loved ones, such as friends and family. You can even have other favorite idols like actors and comedians to ask people to leave voice messages for you when you’re not available!

We’d love to hear from you at Interspeech! Team ObEN will be around to demonstrate our ideas and demos at Booth 4 at the conference, and ObENing up one during Happy Hour for prospective applicants to meet our speech team on September 10th from 5:00 to 6:30pm with some complimentary bottle ObENers!

Get more details about Happy Hour

Meanwhile, those who’d like to sound off their excitement in other parts of the world besides San Francisco, there’s a lot you can do to keep a conversation going with us.

First, there’s always leaving a comment below. There’s also reading more about us to know what to ask or request by contacting us. For those of you feeling up to the same challenges and passions we have for having a say in the future of our voice technology and the ‘Virtual Me’, you can also check out our the careers we have up; we’re currently searching far and wide for speech scientists, machine learning engineers, and software developers to fully realize our vision for bringing our voice and virtual image everywhere.

About the author: Dustin is a Marketing Associate at ObEN


ObEN的专利人工智能技术能够迅速将一个人的平面图像和声音结合起来,创造3D虚拟形象。将你的个人3D虚拟形象复制到任何虚拟现实或者增强现实的情境中,享受更深刻,记忆更持久的社交体验。创始于2014年,ObEN是HTC旗下VIVE X速创项目计划中的公司之一,目前在加州帕萨迪纳的领先科技孵化器创意工作室内办公。