EARSHOT: A minimal network model of human speech recognition that operates on real speech.
James S. MagnusonHeejo YouJay G. RuecklPaul D. AllopennaMonica LiSahil LuthraRachael SteinerHosung NamMonty EscabiKevin S. BrownRachel M. TheodoreNicholas MontoPublished in: CogSci (2019)
Keyphrases
- speech recognition
- network model
- speech signal
- automatic speech recognition
- speech synthesis
- speech recognizer
- speech processing
- hidden markov models
- speech recognition technology
- speech recognition systems
- language model
- speaker identification
- speech recognizers
- pattern recognition
- noisy environments
- speaker dependent
- recognition engine
- keyword spotting
- cepstral coefficients
- speech recognition errors
- noisy speech
- neural network
- handwriting recognition
- speaker independent
- isolated word
- word error rate
- speech retrieval
- probabilistic model