Graph-Based Semisupervised Learning for Acoustic Modeling in Automatic Speech Recognition.
Yuzong LiuKatrin KirchhoffPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2016)
Keyphrases
- automatic speech recognition
- semisupervised learning
- acoustic features
- speech recognition
- speech sounds
- speech recognizers
- speech signal
- word error rate
- hidden markov models
- broadcast news
- acoustic models
- conversational speech
- semi supervised
- noisy environments
- speech retrieval
- semi supervised learning
- spontaneous speech
- feature space
- decision trees
- pairwise
- information retrieval
- unlabeled data
- supervised learning
- machine learning
- speech corpus
- data mining