Language model and speaking rate adaptation for spontaneous presentation speech recognition.
Hiroaki NanjoTatsuya KawaharaPublished in: IEEE Trans. Speech Audio Process. (2004)
Keyphrases
- speech recognition
- language model
- rate adaptation
- language modeling
- wireless networks
- document retrieval
- video streaming
- probabilistic model
- n gram
- automatic speech recognition
- test collection
- speech signal
- retrieval model
- word error rate
- information retrieval
- mixture model
- query expansion
- video streams
- handwriting recognition
- translation model
- multimedia
- query terms
- generative model
- cross lingual
- hidden markov models
- statistical machine translation
- feature selection