Otter is available as an app or on desktop as a real time speech recognition service that can recognise different speakers in recorded sessions. The app creates smart voice notes that combine audio, transcription, speaker identification, inline photos, and key phrases.
It is remarkably accurate even when using a desktop microphone with clear English speakers in a small room. Useful for note taking and transcribing interviews. Works on mobiles and tablets with a Premium version offering many more features such as names of speakers when they register and are recognised by recording a little bit of speech.
“Players earn points for imitating the 26 letters of the alphabet in American Sign Language (ALS), which convolutional neural networks trained on a collection of more than 100,000 images classify in near-real time.” Stradigi AI Carolina Bessega, Stradigi AI’s Chief Scientific Officer says that “The AI system is 99.03 percent accurate at correctly identifying ASL letters, Bessega said. That’s about half a percentage point better than Google’s pretrained Inception V4 managed in the company’s tests (98.50 percent), and nearly two percent better than the popular Xception algorithm (97.37 percent).” Search for:Search
“Hearing AI aims to connect people to the world of sound. The interface allows people to visualize the intensity of environmental sounds in order to gauge the ambience of a physical space. Hearing AI distinguishes between four different types of sound environments and notifies people if there are sudden changes or if sounds are damaging to their ears. In addition, Hearing AI uses real-time speech-to-text technology to transcribe verbal conversations with an emphasis on visualizing the loudness of speech through typography. Key Features:
Visualizations: See the activity, volume, and ambience of the sounds around you. What’s the sound level in the environment? Is it loud enough to damage your ears? Hearing AI will let you know.
Notifications: Get customizable notifications whenever Hearing AI detects sudden changes and important sounds.
Speech-To-Text: Be able to not only read spoken conversation, but see the volume of speech excerpts in real-time.” Microsoft Garage Team