Improving robustness of speech recognition performance to aggregate of noises by two-dimensional visualization.
Makoto ShozakaiGoshu NaginoPublished in: INTERSPEECH (2005)
Keyphrases
- speech recognition
- hidden markov models
- language model
- speech recognizer
- speech processing
- speech synthesis
- pattern recognition
- automatic speech recognition
- speech understanding
- speech recognition technology
- handwriting recognition
- speech recognition systems
- speaker identification
- speech recognizers
- noisy environments
- speech signal
- speech recognition errors
- speaker independent
- speech retrieval
- keyword spotting
- machine learning
- audio visual speech recognition
- speaker recognition
- signal processing
- natural language processing
- feature extraction