Time-frequency convolutional networks for robust speech recognition.
Vikramjit MitraHoracio FrancoPublished in: ASRU (2015)
Keyphrases
- speech recognition
- noisy environments
- hidden markov models
- speech processing
- speech signal
- speech synthesis
- language model
- pattern recognition
- speech understanding
- automatic speech recognition
- speech recognition technology
- speaker identification
- speech recognizer
- speech retrieval
- handwriting recognition
- speaker independent
- keyword spotting
- speaker dependent
- neural network
- audio visual
- visual features
- maximum likelihood
- speech recognizers