Improving Speaker Discrimination of Target Speech Extraction With Time-Domain Speakerbeam.
Marc DelcroixTsubasa OchiaiKaterina ZmolíkováKeisuke KinoshitaNaohiro TawaraTomohiro NakataniShoko ArakiPublished in: ICASSP (2020)
Keyphrases
- speech recognition
- speaker recognition
- automatic speech recognition
- audio visual
- speaker identification
- speaker verification
- automatic speech recognition systems
- prosodic features
- speech signal
- frequency domain
- information extraction
- speaker dependent
- speaker diarization
- automatic extraction
- automatic transcription
- speaker adaptation
- speech synthesis
- synthesized speech
- target tracking
- feature selection
- vocal tract
- text to speech
- data mining
- gaussian mixture model
- emotion recognition
- multi modal
- multimedia
- hidden markov models
- probabilistic neural network
- moving target
- vector quantization