Subword-based multi-span pronunciation adaptation for recognizing accented speech.
Timo MertensKit ThambiratnamFrank SeidePublished in: ASRU (2011)
Keyphrases
- speech recognition
- speaker adaptation
- automatic speech recognition
- broadcast news
- speech recognizer
- spontaneous speech
- spoken document retrieval
- speech signal
- speech synthesis
- hidden markov models
- pattern recognition
- acoustic models
- speaker independent
- language model
- automatic recognition
- speech recognition systems
- recognition engine
- noisy environments
- text to speech
- speaker identification
- language learning
- neural network
- grapheme to phoneme conversion
- information extraction
- machine learning