Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home.
Chanwoo KimAnanya MisraKean K. ChinThad HughesArun NarayananTara N. SainathMichiel BacchianiPublished in: INTERSPEECH (2017)
Keyphrases
- speech recognition
- neural network
- pattern recognition
- speech synthesis
- language model
- hidden markov models
- speech recognizer
- speech signal
- speech processing
- speech recognition technology
- automatic speech recognition
- noisy environments
- speech recognition systems
- speech understanding
- speaker identification
- speaker independent
- speaker dependent
- natural language
- speaker diarization
- speech recognition errors
- speech retrieval
- data mining
- multilayer perceptron
- feature extraction
- feature selection
- computer vision
- search engine
- keyword spotting