Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches.
Naoyuki KandaYusuke FujitaShota HoriguchiRintaro IkeshitaKenji NagamatsuShinji WatanabePublished in: ICASSP (2019)
Keyphrases
- speech recognition
- multi channel
- speech recognition systems
- speaker independent
- speech recognizers
- hidden markov models
- speech signal
- language model
- single channel
- automatic speech recognition
- speech synthesis
- acoustic models
- speech recognition technology
- sound source
- pattern recognition
- speech recognizer
- speech processing
- noisy speech
- speaker identification
- audio visual speech recognition
- speech retrieval
- multiresolution
- computer vision
- acoustic features
- audio visual
- speaker dependent
- denoising
- information retrieval