Listen to Story A team of researchers from the International Institute of Information Technology (IIIT) Hyderabad has developed an innovative Silent Speech Interface (SSI) that can convert non-audible murmurs into vocalised speech. This groundbreaking technology has the potential to improve communication for people with speech impairments. The research team, led by TCS researcher and PhD student Neil Shah, along with Neha Sahipjohn and Vishal Tambrahalli, worked under the guidance of Dr Ramanathan Subramanian and Prof Vineet Gandhi.
Their findings are published in a paper titled "StethoSpeech: Speech Generation Through a Clinical Stethoscope Attached to the Skin," which was presented at the UBIcomp/ISWC conference in Melbourne, Australia. WHAT IS SILENT SPEECH INTERFACE (SSI)? Silent Speech Interface (SSI) is a form of communication where no sound is produced audibly. Neil Shah explained, "The most common form of SSI is lip reading, but there are other techniques like Ultrasound Tongue Imaging, real-time MRI, and Electromagnetic Articulography.
However, these methods can be highly invasive and don't work in real-time." To address these challenges, the IIITH team used a stethoscope attached behind the ear to capture Non-Audible Murmurs (NAM) and convert them into intelligible speech. StethoSpeech converts flesh-conducted vibrations into intelligible speech.
(Photo: IIIT-Hyderabad) "We wanted to create a solution for people with voice disorders to help them engage in social int.
