From Undercomplete to Sparse Overcomplete Autoencoders to Improve LF-MMI based Speech Recognition.
Selen Hande KabilHervé BourlardPublished in: INTERSPEECH (2022)
Keyphrases
- speech recognition
- automatic speech recognition
- pattern recognition
- speech synthesis
- language model
- hidden markov models
- speech recognizer
- speech processing
- speech signal
- speech understanding
- noisy environments
- speech recognition technology
- denoising
- speaker identification
- speaker recognition
- sparse representation
- speech recognition errors
- speech retrieval
- feature extraction
- acoustic models
- high dimensional
- speech recognition systems
- keyword spotting
- information retrieval
- isolated word
- audio visual speech recognition