LRS3-TED

VideosCreative Commons BY-NC-ND 4.0 license

LRS3-TED is a multi-modal dataset for visual and audio-visual speech recognition. It includes face tracks from over 400 hours of TED and TEDx videos, along with the corresponding subtitles and word alignment boundaries. The new dataset is substantially larger in scale compared to other public datasets that are available for general research.

Source: LRS3-TED: a large-scale dataset for visual speech recognition

Benchmarks

Active Speaker Detection/Accuracy Audio-Visual Speech Recognition/Word Error Rate (WER)Automatic Speech Recognition (ASR)/WER Automatic Speech Recognition (ASR)/Word Error Rate (WER)Keyword Spotting/Top-1 Accuracy Keyword Spotting/Top-5 Accuracy Keyword Spotting/mAP Keyword Spotting/mAP IOU@0.5 Lipreading/Word Error Rate (WER)Natural Language Transduction/Word Error Rate (WER)Speech Recognition/Word Error Rate (WER)Speech Recognition/WER Visual Speech Recognition/Word Error Rate (WER)