Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling.
Jaejin ChoMurali Karthick BaskarRuizhi LiMatthew WiesnerSri Harish Reddy MallidiNelson YaltaMartin KarafiátShinji WatanabeTakaaki HoriPublished in: CoRR (2018)
Keyphrases
- speech recognition
- language model
- language modeling
- transfer learning
- cross lingual
- hidden markov models
- information retrieval
- retrieval model
- document retrieval
- word error rate
- n gram
- query expansion
- probabilistic model
- pattern recognition
- computer vision
- labeled data
- semi supervised learning
- unlabeled data
- machine learning algorithms
- digital libraries
- multimedia
- image processing
- automatic speech recognition
- data sets