Instruction Data Generation and Unsupervised Adaptation for Speech Language Models.
Vahid NorooziZhehuai ChenSomshubra MajumdarSteve HuangJagadeesh BalamBoris GinsburgPublished in: CoRR (2024)
Keyphrases
- language model
- data generation
- speech recognition
- word error rate
- language modeling
- document retrieval
- spoken term detection
- speech signal
- probabilistic model
- n gram
- information retrieval
- language modelling
- data streams
- active learning
- query expansion
- automatic speech recognition
- streaming data
- test collection
- multimedia
- smoothing methods
- statistical language models
- retrieval model
- semi supervised
- supervised learning
- unsupervised learning
- out of vocabulary
- co training
- high throughput
- document ranking
- okapi bm
- data sets
- relevance model
- prior knowledge
- language models for information retrieval
- semi supervised learning