Likelihood-maximizing beamforming for robust hands-free speech recognition.
Michael L. SeltzerBhiksha RajRichard M. SternPublished in: IEEE Trans. Speech Audio Process. (2004)
Keyphrases
- speech recognition
- noisy environments
- language model
- speech synthesis
- hidden markov models
- pattern recognition
- speech signal
- hands free
- speech recognition technology
- speech recognizer
- speech enhancement
- speaker identification
- automatic speech recognition
- speaker independent
- computer vision
- maximum likelihood
- image processing
- human computer interaction
- mixture model
- multi modal
- spoken language
- user interface
- image retrieval
- expert systems
- feature selection
- machine learning