
AI translation startup led by UW computer science whiz enables ‘superhuman hearing capabilities'
GeekWire's startup coverage documents the Pacific Northwest entrepreneurial scene. Sign up for our weekly startup newsletter , and check out the GeekWire funding tracker and venture capital directory .
Shyam Gollakota.
A new Seattle startup is taking speech translation to a whole new dimension.
Hearvana, founded this year by University of Washington computer science researchers, translates speech from multiple speakers in real time — while preserving their spatial positions and vocal identities.
The idea is that you could be in a noisy setting surrounded by people speaking different languages, and still understand what's being said.
'Our system transforms your entire auditory space into your own language, preserving the unique voices of speakers, their 3D spatial positions, and doing it all in real time, even as people move,' Shyam Gollakota, co-founder of Hearvana, wrote on LinkedIn.
Gollakota, a leading inventor who heads up the UW's Mobile Intelligence Lab, told GeekWire that the company is 'creating AI breakthroughs that are shaping the future of sound.'
'Our AI algorithms enable on-device superhuman hearing capabilities and will be part of billions of earbuds, hearing aids and smartphones,' he said. 'It is an exciting time.'
Hearvana says its translation features go beyond what's available on existing wearables such as Meta's Ray-Ban glasses.
The startup's underlying tech — dubbed 'spatial speech translation' — was detailed in a research paper published last month. The study tested translation from French, German, and Spanish into English. It outperformed baseline systems in user studies and participants praised its translation accuracy, speaker fidelity, and spatial realism.
Hearvana is being incubated at the AI2 Incubator in Seattle.
'Hearvana is my favorite kind of startup as it addresses a familiar pain point — we all struggle to hear in noisy settings like a restaurant or a party — with deep AI technology,' said Oren Etzioni, technical director and partner at AI2 Incubator.
Etzioni, the former CEO of the Allen Institute for AI, called Gollakota a 'world-class computer scientist.'
Hearvana co-founder Malek Itani.
Gollakota has a track record of turning research into startups.
He previously co-founded Sound Life Sciences, a UW spinout that developed an app to monitor breathing that was acquired by Google in 2022.
He's also the co-founder of Wavely Diagnostics, which uses a smartphone app to detect ear infections.
Gollakota last year won a $100,000 award as one of six researchers honored as part of this year's Infosys Prize.
His research focuses on wireless tech, battery-free devices, WiFi sensing and imaging, medical diagnostics via smartphones, and more.
Malek Itani, a research assistant and PhD student at the UW's computer science school, is a co-founder of Hearvana. Itani was an intern at Meta, where he worked on smart glasses.
Gollakota and Itani published research last year on a headphone prototype that uses AI to create a 'sound bubble' and can learn the distance for each sound source in a room.
Hashtags

Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles


Bloomberg
8 minutes ago
- Bloomberg
Nvidia, Samsung Plan Investments in Robotics Startup Skild AI
Samsung Electronics Co. and Nvidia Corp. will take minority stakes in Skild AI Inc. as they seek to bolster their work in the emerging consumer robotics industry. The South Korean tech leader is making a $10 million investment in Skild, which develops software for robots, according to people with knowledge of the matter. The Santa Clara, California chipmaker is putting in $25 million, said the people, who asked not to be identified discussing unannounced plans.


Bloomberg
16 minutes ago
- Bloomberg
Gold Advances on Middle East Tensions and Trump's Tariff Pledge
Gold gained for a second day on increased tensions in the Middle East, with its haven status also supported by President Donald Trump's comments that he will inform trading partners on tariff rates within two weeks. Bullion rose as much as 0.6% to around $3,373 an ounce, extending a 1% gain from the earlier session when it was also boosted by a declining dollar. Buying interest increased after the US ordered some embassy staff to depart Baghdad and allowed military families to leave the Middle East, after Iran threatened to attack US bases if talks over its nuclear program fell through.


Fast Company
23 minutes ago
- Fast Company
Enough hype about AI in health—let's talk about results
There's no shortage of big promises about AI in healthcare. The U.S. government announced a $500 billion Stargate initiative to fund AI infrastructure, while the UK government announced £82.6 million in research funding for three projects, two of which are using AI to tackle cancer and Alzheimer's disease. But ask any patient waiting for a diagnosis, or a clinician searching for certainty, and the real question cuts through all the noise: When will all the innovation deliver real impact where it matters most? We've entered an era where healthcare data is measured in exabytes—genomes, images, clinical notes, labs, and signals from every continent. At SOPHiA GENETICS, we've just achieved the milestone of analyzing 2 million patient profiles. It's a number that was unimaginable a decade ago. Yet the value of data isn't in volume. It's what you do with it. Insight matters only if it changes an outcome, shortens a diagnostic odyssey, or opens up a new chance for a patient. It's time to move from conversation to action. Too often, insights get trapped in institutional silos or left in endless pilot projects, just out of reach of the people who need them. 3 ways AI is already transforming medicine Today, technology can connect, for example, a patient in São Paulo with expertise in Seoul, uncovering patterns invisible to the human eye. Here are several ways AI is helping now. 1. Improving diagnostic accuracy: AI algorithms, particularly those based on deep learning, have demonstrated remarkable accuracy in diagnosing diseases from medical images and test results. These systems are trained on vast datasets, allowing them to recognize patterns and anomalies that might be missed by the human eye. For example, in dermatology, AI systems trained on images of skin lesions have shown the ability to detect skin cancers, such as melanoma, with high levels of precision. 2. Enhancing cancer prevention: AI techniques can be used to screen individuals for genomic markers and develop personalized cancer risk prediction scores. This proactive approach can help screen younger patients for genomic predispositions, empowering them to make informed prevention decisions and proactively monitor their health. 3. Tailoring treatments to genomic profiles: One of the most significant applications of AI is in the field of genomics. AI can analyze vast genomic datasets to identify mutations and variations that might influence an individual's response to certain treatments. For example, our SOPHiA DDM product can identify specific genomic markers that are susceptible to targeted cancer therapies, increasing the efficacy of the treatment and minimizing the risk of adverse reactions, for a more effective and safer treatment plan for patients. To scale up these AI applications there are many regulatory and compliance barriers to overcome. This requires investment in data security, creating clear guidelines, data security measures, and ensuring clinicians are fully trained. Our goal should be to create a regulatory environment that fosters innovation while safeguarding patient data and promoting public trust. We must democratize this powerful data to enable more physicians, practices, and hospitals to incorporate AI into daily clinical use so that a greater number of patients can access data-driven medicine, not just a select few. My message for governments investing in AI is clear: Balance investing in future AI tools with validating existing solutions that have already been proven to improve patient outcomes. Build the bridges that turn breakthroughs into benefits, so that data-driven medicine becomes a reality for every patient.