Untranscribed Web Audio for Low Resource Speech Recognition.
Andrea CarmantiniPeter BellSteve RenalsPublished in: INTERSPEECH (2019)
Keyphrases
- speech recognition
- speaker identification
- speech processing
- speech recognition technology
- automatic speech recognition
- language model
- hidden markov models
- audio visual speech recognition
- speech synthesis
- speech signal
- speech understanding
- pattern recognition
- speech recognizer
- noisy environments
- speech retrieval
- speech recognition systems
- web pages
- isolated word
- broadcast news
- multimedia
- cepstral coefficients
- visual information
- speech recognition errors
- speaker dependent
- speaker independent
- neural network
- feature vectors
- keyword spotting
- speaker diarization
- multi stream
- audio signals
- feature extraction
- bayesian networks
- audio visual
- mobile devices