Personal VAD: Speaker-Conditioned Voice Activity Detection.
Shaojin DingQuan WangShuo-Yiin ChangLi WanIgnacio Lopez-MorenoPublished in: CoRR (2019)
Keyphrases
- voice activity detection
- speech recognition
- noisy environments
- speaker verification
- speaker identification
- automatic speech recognition
- speaker recognition
- personal information
- language model
- noise reduction
- speech signal
- speaker diarization
- audio visual
- hidden markov models
- gaussian mixture model
- multi modal
- prosodic features
- speaker adaptation
- computer vision
- speech synthesis
- feature vectors
- image processing