Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition.
Tara N. SainathRon J. WeissKevin W. WilsonBo LiArun NarayananEhsan VarianiMichiel BacchianiIzhak ShafranAndrew W. SeniorKean K. ChinAnanya MisraChanwoo KimPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2017)
Keyphrases
- automatic speech recognition
- signal processing
- neural network
- speech recognition
- pattern recognition
- speech signal
- word error rate
- hidden markov models
- broadcast news
- conversational speech
- linear prediction
- image processing
- speech retrieval
- spoken words
- acoustic features
- single channel
- noisy environments
- word recognition
- language model
- multi channel
- question answering
- document retrieval
- spontaneous speech
- recognition errors
- speech corpus
- multiscale
- computer vision