Two figures. The top one shows "The EfficientPunct framework. The top branch predicts using text only, while the bottom branch predicts using text and audio.". The bottom one shows "Filtering pipeline used to create SponSpeech. Blue indicates a text-based filter, and yellow indicates an audio-based filter, also shown by the bottom-right icons. The evaluation criteria are represented by the sub-boxes within the subtitle, quality, and appropriateness filters."

Research

AI That Adds Meaning, One Comma at a Time

Professor Homayoon Beigi’s new approach to speech recognition could make voice-to-text systems smarter and more human-like.

April 03, 2025
Xintian Tina Wang