SpeakerBeam: Speaker Aware Neural Network for Target Speaker Extraction in Speech Mixtures.
Katerina ZmolíkováMarc DelcroixKeisuke KinoshitaTsubasa OchiaiTomohiro NakataniLukás BurgetJan CernockýPublished in: IEEE J. Sel. Top. Signal Process. (2019)
Keyphrases
- speech recognition
- speaker recognition
- neural network
- speaker verification
- audio visual
- automatic speech recognition
- speaker identification
- speaker dependent
- prosodic features
- speaker diarization
- automatic speech recognition systems
- probabilistic neural network
- synthesized speech
- speech signal
- speech synthesis
- vocal tract
- acoustic features
- pattern recognition
- gaussian mixture model
- genetic algorithm
- automatic transcription
- mixture model
- artificial neural networks
- information extraction
- speech recognizer
- multilayer perceptron
- text to speech
- speaker adaptation
- noisy environments
- hidden markov models
- self organizing maps
- bp neural network
- human computer interaction
- moving target
- mel frequency cepstral coefficients
- speaker independent
- multi modal
- fuzzy logic
- phoneme recognition
- broadcast news