Joint Uncertainty Decoding (JUD) with Histogram-Based Quantization (HQ) for Robust and/or Distributed Speech Recognition.
Chia-Yu WanLin-Shan LeePublished in: ICASSP (1) (2006)
Keyphrases
- speech recognition
- noisy environments
- hidden markov models
- speech signal
- pattern recognition
- speech synthesis
- automatic speech recognition
- speech processing
- speech recognizer
- speech understanding
- speaker identification
- speech recognition technology
- speech recognition systems
- language model
- keyword spotting
- speech retrieval
- speaker independent
- image processing
- speech recognition errors
- data mining