Deep ad-hoc beamforming based on speaker extraction for target-dependent speech separation.
Ziye YangShanzheng GuanXiao-Lei ZhangPublished in: Speech Commun. (2022)
Keyphrases
- speech recognition
- audio visual
- sound source
- speaker recognition
- automatic speech recognition
- speaker verification
- speech signal
- speech enhancement
- speaker identification
- vocal tract
- speaker dependent
- prosodic features
- automatic speech recognition systems
- speaker diarization
- noisy environments
- speech synthesis
- automatic extraction
- target tracking
- information extraction
- linear array
- frequency domain
- gaussian mixture model
- audio features
- speech sounds
- acoustic features
- automatic transcription
- broadcast news
- pattern recognition
- multimedia
- vector quantization
- blind source separation
- moving target
- feature extraction
- hidden markov models
- speaker adaptation
- visual information
- acoustic models
- speaker independent
- mel frequency cepstral coefficients
- linear prediction
- deep learning
- spoken language
- single channel