speech recognition
Technology
NVIDIA researchers win first place in Telugu ASR competition
Though it’s among the most widely spoken languages in the world, Telugu has few high-quality ASR models available for it, and is classified as a low-resource language.
Technology
Training AI to read your lips — in multiple languages
While most speech recognition tools analyze audio alone, researchers have also made progress in developing visual speech recognition (VSR) models, which rely on visual input to identify what a speaker is saying.
Technology
Researchers share framework for more accurate speech recognition
In their paper, published at the end of August, the researchers outline their approach to improving ASR for Mandarin Chinese, which was found to reduce character error rates by more than 25%.
Business
Youtube to Add Several New Audio and Caption Features
Google recently announced last week that it will be adding a whole new series of features to Youtube’s closed captioning and subtitles, including a...
Technology
WhatsApp Developing Automatic Transcription Feature
WhatsApp is currently working on developing an in-app speech recognition and automatic transcription system for the iOS app’s voice message feature, according to WhatsApp...
Press Release
KUDO Launches Live Captioning for Multilingual Meetings, Doubling Down on Commitment to Equity and Inclusion
NEW YORK, Sept. 13, 2021 -- KUDO Inc., the multilingual meeting SaaS company built around a B2B managed marketplace powered by the largest network of professional conference...
Culture
The Underrepresentation of African Languages in Tech
Like any other continent on Earth, Africa is home to hundreds — and potentially thousands, depending on who you ask—of indigenous languages. Some of...
Technology
Developing More Accessible Speech Recognition Systems
Researchers at Facebook have developed an artificial intelligence (AI) system that doesn’t need transcribed audio data to recognize speech — this means that the...