Using Presentation Slides and Adjacent Utterances for Post-editing of Speech Recognition Results for Meeting Recordings.
Kentaro KamiyaTakuya KawaseRyuichiro HigashinakaKatashi NagaoPublished in: TDS (2021)
Keyphrases
- speech recognition
- speaker diarization
- hidden markov models
- language model
- speech signal
- pattern recognition
- speech synthesis
- automatic speech recognition
- speech recognizer
- speech processing
- multimedia
- noisy environments
- speech recognition technology
- speech understanding
- acoustic features
- isolated word
- speaker identification
- speech retrieval
- speaker independent
- speech recognition systems
- word error rate
- natural language
- handwriting recognition
- speaker adaptation
- spontaneous speech
- speaker dependent
- multi modal
- audio visual