An effective two-stage key frame extraction method for speech-visual emotion recognition

Yuanhui Liang, Xiaojing Li, Lei Wang · 2026

Read An effective two-stage key frame extraction method for speech-visual emotion recognition by Yuanhui Liang, Xiaojing Li, Lei Wang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13332150.txt.

Description

Yuanhui Liang and co-authors present a two-stage method for picking key frames in speech-visual emotion recognition, in a 2026 paper. Systems that read emotion from voice and face face two problems. Frame selection often keeps redundant frames or drops telling ones. Fusion methods that merge voice and face can also be hard to interpret.

The first stage scores visual frames by information entropy. That models how emotion builds over time and trims redundancy. Matching speech key frames are then selected in stage two. The method aims to keep emotional peaks while cutting noise. Cleaner inputs should lift recognition accuracy. Human-computer interaction tools, from tutoring to telehealth, stand to gain. The design also keeps the process explainable.

Catalog record

CREATORYuanhui Liang, Xiaojing Li, Lei Wang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE37 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13332150

Browse the full library · About the Tower of Babel