speech recognition

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.

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.

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%.

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...

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...

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...

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...

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...