Discriminative re-ranking for automatic speech recognition by leveraging invariant structures.
Masayuki SuzukiGakuto KurataMasafumi NishimuraNobuaki MinematsuPublished in: Speech Commun. (2015)
Keyphrases
- automatic speech recognition
- discriminative training
- speech recognition
- speech signal
- speech retrieval
- hidden markov models
- ranking algorithm
- broadcast news
- word recognition
- word error rate
- spoken words
- conversational speech
- recognition errors
- spontaneous speech
- noisy environments
- speech corpus
- ranked list
- information extraction
- feature extraction
- acoustic features
- search engine
- image classification
- feature selection
- speech sounds
- computer vision