Live Streaming Speech Recognition Using Deep Bidirectional LSTM Acoustic Models and Interpolated Language Models.
Javier JorgeAdrià GiménezJoan Albert Silvestre-CerdàJorge CiveraAlberto SanchísAlfons JuanPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2022)
Keyphrases
- language model
- speech recognition
- acoustic models
- live streaming
- speech recognizer
- speaker independent
- language modeling
- automatic speech recognition
- peer to peer
- speech signal
- n gram
- probabilistic model
- document retrieval
- information retrieval
- query expansion
- retrieval model
- speech recognition systems
- test collection
- speaker identification
- broadcast news
- noisy environments
- hidden markov models
- query terms
- mixture model
- relevance model
- pattern recognition
- multimedia content
- computer vision
- machine learning