Unsupervised Stemming based Language Model for Telugu Broadcast News Transcription.
Mythili Sharan PalaParayitam LaxminarayanaA. V. RamanaPublished in: CoRR (2019)
Keyphrases
- language model
- broadcast news
- n gram
- spoken term detection
- automatic speech recognition
- speech recognition
- language modeling
- out of vocabulary
- word level
- information retrieval
- document retrieval
- query expansion
- retrieval effectiveness
- probabilistic model
- retrieval model
- spoken document retrieval
- document images
- semi supervised
- handwriting recognition
- unsupervised learning
- video search
- word error rate
- test collection
- speaker diarization
- language independent
- video retrieval
- bag of words
- word segmentation
- query terms
- mixture model
- pattern recognition
- term dependencies
- language processing
- translation model
- speech signal
- text retrieval
- video data
- image retrieval
- feature selection