Out-of-Vocabulary Word Recovery using FST-Based Subword Unit Clustering in a Hybrid ASR System.
Ekaterina EgorovaLukás BurgetPublished in: ICASSP (2018)
Keyphrases
- out of vocabulary
- broadcast news
- spoken document retrieval
- language model
- n gram
- automatic speech recognition
- word segmentation
- cross language information retrieval
- speech recognition
- speech recognizer
- named entity recognition
- query words
- k means
- clustering method
- clustering algorithm
- cross lingual
- parallel corpora
- hand crafted
- named entities
- language modeling
- query terms
- information retrieval
- term frequency
- machine translation
- unsupervised learning
- query translation
- test collection
- text classification
- probabilistic model
- information access
- retrieval model