Latent perceptual mapping with data-driven variable-length acoustic units for template-based speech recognition.
Shiva SundaramJerome R. BellegardaPublished in: ICASSP (2012)
Keyphrases
- variable length
- speech recognition
- data driven
- speech recognition systems
- fixed length
- speaker independent
- speech recognizers
- speech processing
- acoustic models
- language model
- n gram
- hidden markov models
- speech recognizer
- speech synthesis
- noisy speech
- speech signal
- pattern recognition
- automatic speech recognition
- speech recognition technology
- speaker identification
- bitstream
- machine learning
- latent variables
- noisy environments
- sound source
- image processing
- speech retrieval
- feature selection
- information retrieval