AG-LSEC: Audio Grounded Lexical Speaker Error Correction.
Rohit PaturiXiang LiSundararajan SrinivasanPublished in: CoRR (2024)
Keyphrases
- error correction
- audio visual
- speaker identification
- prosodic features
- audio stream
- automatic transcription
- speaker verification
- speech recognition
- multimedia
- visual information
- speaker diarization
- error detection
- wordnet
- emotion recognition
- acoustic features
- error correcting
- speaker recognition
- channel coding
- broadcast news
- visual data
- watermarking scheme
- error detection and correction
- automatic speech recognition
- text to speech
- data hiding
- magnetic tape
- error analysis
- visual speech
- gaussian mixture model
- error control
- hidden markov models