Speaker-adapted confidence measures for speech recognition of video lectures.
Isaias Sanchez-CortinaJesús Andrés-FerrerAlberto SanchísAlfons JuanPublished in: Comput. Speech Lang. (2016)
Keyphrases
- speech recognition
- confidence measures
- ground truth
- automatic speech recognition
- speaker identification
- stereo vision
- hidden markov models
- language model
- confidence measure
- video data
- speaker dependent
- speech synthesis
- multimedia
- video sequences
- speech recognizer
- speech processing
- speech signal
- noisy environments
- video frames
- pattern recognition
- optical flow
- speaker adaptation
- speech recognition technology
- digital video library
- speaker diarization
- speaker independent
- acoustic models
- video content
- real time
- speech recognition systems
- key frames
- vocal tract
- cepstral coefficients
- computer vision