Yihan Wu

EVA combines audio and visual signals for better speech recognition accuracy.

2025-06-07T22:08:20+00:00 ― 4 min read

ESPnet-Codec enhances training and evaluation of neural codecs for audio and speech.

2025-06-03T03:09:30+00:00 ― 7 min read

Learn how AV-ASR combines audio and visuals for better speech recognition.

2025-01-24T21:39:36+00:00 ― 6 min read