Extending Whisper with Prompt Tuning to Target-Speaker ASR.
Hao MaZhiyuan PengMingjie ShaoJing LiJu LiuPublished in: ICASSP (2024)
Keyphrases
- automatic speech recognition
- speech recognition
- noisy environments
- speaker recognition
- speech signal
- speaker verification
- hidden markov models
- parameter settings
- moving target
- target tracking
- broadcast news
- spoken words
- real time
- conversational speech
- rule selection
- speaker identification
- target detection
- error rate
- multi modal
- feature extraction
- databases