Deep long short-term memory adaptive beamforming networks for multichannel robust speech recognition.
Zhong MengShinji WatanabeJohn R. HersheyHakan ErdoganPublished in: ICASSP (2017)
Keyphrases
- speech recognition
- noisy environments
- language model
- hidden markov models
- speech enhancement
- speech processing
- speech signal
- speech recognizer
- speech synthesis
- speech understanding
- automatic speech recognition
- pattern recognition
- speech recognition systems
- speaker identification
- speech recognizers
- speech retrieval
- audio visual speech recognition
- natural language processing
- frequency domain
- speaker independent
- speaker dependent
- speech recognition errors
- computer vision
- speech recognition technology
- machine learning
- isolated word
- neural network