Supervised and unsupervised active learning for automatic speech recognition of low-resource languages.
Ali Raza SyedAndrew RosenbergEllen KislalPublished in: ICASSP (2016)
Keyphrases
- automatic speech recognition
- active learning
- semi supervised
- supervised learning
- speech recognition
- unsupervised learning
- speech signal
- unsupervised methods
- compound words
- learning algorithm
- conversational speech
- word error rate
- hidden markov models
- labeled data
- supervised methods
- speech retrieval
- broadcast news
- unlabeled data
- spoken words
- language independent
- noisy environments
- word recognition
- acoustic features
- recognition errors
- training set
- spontaneous speech
- pos taggers
- speech corpus
- machine learning
- neural network
- error rate
- relevance feedback
- speech sounds
- image processing
- feature selection