Neural Speaker Extraction with Speaker-Speech Cross-Attention Network.
Wupeng WangChenglin XuMeng GeHaizhou LiPublished in: Interspeech (2021)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- speaker verification
- automatic speech recognition
- speaker identification
- network architecture
- speaker diarization
- prosodic features
- speaker dependent
- synthesized speech
- speech signal
- automatic speech recognition systems
- vocal tract
- hebbian learning
- speech recognizer
- neural network
- automatic transcription
- multi modal
- computer networks
- speech synthesis
- complex networks
- wireless sensor networks
- information extraction
- spontaneous speech
- language model
- network model
- communication networks
- speaker adaptation
- noisy environments
- peer to peer
- recurrent networks
- gaussian mixture model
- emotion recognition
- visual data
- mel frequency cepstral coefficients
- spiking neural networks
- lateral inhibition
- phoneme recognition
- speech sounds
- network structure
- hidden markov models