Speaker Separation Using Speaker Inventories and Estimated Speech.
Peidong WangZhuo ChenDeLiang WangJinyu LiYifan GongPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2021)
Keyphrases
- speech recognition
- speaker recognition
- speaker verification
- audio visual
- automatic speech recognition
- speaker identification
- speaker diarization
- prosodic features
- speaker dependent
- vocal tract
- speech synthesis
- gaussian mixture model
- speech signal
- synthesized speech
- noisy environments
- speaker adaptation
- text to speech
- audio stream
- automatic speech recognition systems
- probabilistic neural network
- phoneme recognition
- pattern recognition
- acoustic features
- automatic transcription
- speech sounds
- mel frequency cepstral coefficients
- visual data
- speaker independent
- acoustic models
- visual information
- vector quantization
- mixture model
- dimensionality reduction
- speech recognition systems
- endpoint detection
- hidden markov models
- broadcast news