End-to-End SpeakerBeam for Single Channel Target Speech Recognition.
Marc DelcroixShinji WatanabeTsubasa OchiaiKeisuke KinoshitaShigeki KaritaAtsunori OgawaTomohiro NakataniPublished in: INTERSPEECH (2019)
Keyphrases
- end to end
- speech recognition
- single channel
- multi channel
- hidden markov models
- speech enhancement
- automatic speech recognition
- speech synthesis
- pattern recognition
- language model
- noisy environments
- independent component analysis
- prior information
- frequency domain
- speech signal
- signal processing
- wavelet decomposition
- neural network
- wiener filter
- bayesian networks