Audio augmentation for speech recognition.
Tom KoVijayaditya PeddintiDaniel PoveySanjeev KhudanpurPublished in: INTERSPEECH (2015)
Keyphrases
- speech recognition
- speaker identification
- speech processing
- speech recognition technology
- audio visual speech recognition
- hidden markov models
- cepstral coefficients
- language model
- automatic speech recognition
- speech signal
- multimedia
- speech recognizer
- noisy environments
- speaker recognition
- speech synthesis
- audio visual
- pattern recognition
- speech understanding
- speech recognizers
- speaker independent
- speech recognition systems
- visual data
- signal processing
- voice activity detection
- keyword spotting
- audio signals
- broadcast news
- mel frequency cepstral coefficients
- speech recognition errors
- isolated word
- multi modal
- bayesian networks
- multi stream
- music information retrieval
- speaker dependent
- multimedia information
- visual information