Multi-microphone speech recognition integrating beamforming, robust feature extraction, and advanced DNN/RNN backend.
Takaaki HoriZhuo ChenHakan ErdoganJohn R. HersheyJonathan Le RouxVikramjit MitraShinji WatanabePublished in: Comput. Speech Lang. (2017)
Keyphrases
- speech recognition
- back end
- automatic speech recognition
- feature extraction
- noisy environments
- speaker identification
- pattern recognition
- speaker diarization
- hidden markov models
- cepstral coefficients
- speech synthesis
- speech processing
- frequency domain
- language model
- speech recognizer
- speech signal
- speech recognition systems
- user friendly
- speech recognition technology
- nearest neighbor
- speech enhancement
- image processing
- speech recognizers
- sound source
- building blocks
- speaker independent
- data types
- data management
- feature vectors
- gaussian mixture model
- principal component analysis
- knn
- mobile devices
- preprocessing
- face recognition
- speaker dependent
- database systems
- database