Abstract is missing.
- Improving German Image Captions Using Machine Translation and Transfer LearningRajarshi Biswas, Michael Barz, Mareike Hartmann, Daniel Sonntag. 3-14 [doi]
- Automatic News Article Generation from Legislative Proceedings: A Phenom-Based ApproachAnastasia Klimashevskaia, Richa Gadgil, Thomas Gerrity, Foaad Khosmood, Christian Gütl, Patrick Howe. 15-26 [doi]
- Comparison of Czech Transformers on Text Classification TasksJan Lehecka, Jan Svec. 27-37 [doi]
- Constructing Sentiment Lexicon with Game for Annotation CollectionLukás Radoský, Miroslav Blsták. 38-49 [doi]
- Robustness of Named Entity Recognition: Case of LatvianRinalds Viksna, Inguna Skadina. 50-58 [doi]
- Use of Speaker Metadata for Improving Automatic Pronunciation AssessmentJose Antonio Lopez Saenz, Thomas Hain. 61-72 [doi]
- Augmenting ASR for User-Generated Videos with Semi-supervised Training and Acoustic Model Adaptation for Spoken Content RetrievalYasufumi Moriya, Gareth J. F. Jones. 73-84 [doi]
- Various DNN-HMM Architectures Used in Acoustic Modeling with Single-Speaker and Single-ChannelJosef V. Psutka, Jan Vanek, Ales Prazák. 85-96 [doi]
- Invariant Representation Learning for Robust Far-Field Speaker RecognitionAviad Shtrosberg, Jesús Villalba, Najim Dehak, Azaria Cohen, Bar Ben-Yair. 97-110 [doi]