Abstract is missing.
- Towards User-Centric Text-to-Text Generation: A SurveyDiyi Yang, Lucie Flek. 3-22 [doi]
- Wasserstein Autoencoders with Mixture of Gaussian Priors for Stylized Text GenerationAmirpasha Ghabussi, Lili Mou, Olga Vechtomova. 23-31 [doi]
- Evaluating Semantic Similarity Methods to Build Semantic Predictability Norms of Reading DataSidney Evaldo Leal, Edresson Casanova, Gustavo Paetzold, Sandra M. Aluísio. 35-47 [doi]
- SYN2020: A New Corpus of Czech with an Innovated AnnotationTomás Jelínek, Jan Krivan, Vladimír Petkevic, Hana Skoumalová, Jana Sindlerová. 48-59 [doi]
- Deep Bag-of-Sub-Emotions for Depression Detection in Social MediaJuan S. Lara, Mario Ezra Aragón, Fabio A. González, Manuel Montes-y-Gómez. 60-72 [doi]
- Rewriting Fictional Texts Using Pivot Paraphrase Generation and Character ModificationDou Liu, Tingting Zhu, Jörg Schlötterer, Christin Seifert, Shenghui Wang. 73-85 [doi]
- Transformer-Based Automatic Punctuation Prediction and Word Casing Reconstruction of the ASR OutputJan Svec, Jan Lehecka, Lubos Smídl, Pavel Ircing. 86-94 [doi]
- A Database and Visualization of the Similarity of Contemporary LexiconsGábor Bella, Khuyagbaatar Batsuren, Fausto Giunchiglia. 95-104 [doi]
- The Detection of Actors for GermanManfred Klenner, Anne Göhring. 105-110 [doi]
- Verbal Autopsy: First Steps Towards Questionnaire ReductionAnder Cejudo, Owen Trigueros, Alicia Pérez, Arantza Casillas, Daniel Cobos. 111-123 [doi]
- Effective FAQ Retrieval and Question Matching Tasks with Unsupervised Knowledge InjectionWen-Ting Tseng, Yung-Chang Hsu, Berlin Chen. 124-134 [doi]
- Exploring Conditional Language Model Based Data Augmentation Approaches for Hate Speech ClassificationAshwin Geet D'Sa, Irina Illina, Dominique Fohr, Dietrich Klakow, Dana Ruiter. 135-146 [doi]
- Generating Empathetic Responses with a Pre-trained Conversational ModelJackylyn Beredo, Carlo Migel Bautista, Macario Cordel, Ethel Ong 0001. 147-158 [doi]
- Adaptation of Classic Readability Metrics to CzechKlára Bendová, Silvie Cinková. 159-171 [doi]
- New Parallel Corpora of Baltic and Slavic Languages - Assumptions of Corpus ConstructionMaksim Duszkin, Danuta Roszko, Roman Roszko. 172-183 [doi]
- Use of Augmentation and Distant Supervision for Sentiment Analysis in RussianAnton Golubev, Natalia V. Loukachevitch. 184-196 [doi]
- RobeCzech: Czech RoBERTa, a Monolingual Contextualized Language Representation ModelMilan Straka, Jakub Náplava, Jana Straková, David Samuel. 197-209 [doi]
- Labelled EPIE: A Dataset for Idiom Sense DisambiguationPrateek Saxena, Soma Paul. 210-221 [doi]
- Introducing NYTK-NerKor, A Gold Standard Hungarian Named Entity Annotated CorpusEszter Simon, Noémi Vadász. 222-234 [doi]
- Semantic Templates for Generating Long-Form Technical QuestionsSamiran Pal, Avinash Kumar Singh, Soham Datta, Sangameshwar Patil, Indrajit Bhattacharya, Girish Keshav Palshikar. 235-247 [doi]
- Rethinking Adversarial Training for Language AdaptationGil Rocha, Henrique Lopes Cardoso. 248-260 [doi]
- A Corpus with Wavesurfer and TEI: Speech and Video in TEITOKMaarten Janssen. 261-268 [doi]
- Exploiting Subjectivity Knowledge Transfer for End-to-End Aspect-Based Sentiment AnalysisSamuel Pecar, Marián Simko. 269-280 [doi]
- Towards Personal Data Anonymization for Social MessagingOndrej Sotolár, Jaromír Plhák, David Smahel. 281-292 [doi]
- ParCzech 3.0: A Large Czech Speech Corpus with Rich MetadataMatyás Kopp, Vladislav Stankov, Jan Oldrich Kruza, Pavel Stranák, Ondrej Bojar. 293-304 [doi]
- Using Zero-Shot Transfer to Initialize azWikiNER, a Gold Standard Named Entity Corpus for the Azerbaijani LanguageKamran Ibiyev, Attila Novák. 305-317 [doi]
- Using BERT Encoding and Sentence-Level Language Model for Sentence OrderingMelika Golestani, Seyedeh Zahra Razavi, Zeinab Borhanifard, Farnaz Tahmasebian, Hesham Faili. 318-330 [doi]
- Using Presentation Slides and Adjacent Utterances for Post-editing of Speech Recognition Results for Meeting RecordingsKentaro Kamiya, Takuya Kawase, Ryuichiro Higashinaka, Katashi Nagao. 331-340 [doi]
- Leveraging Inter-step Dependencies for Information Extraction from Procedural Task InstructionsNima Nabizadeh, Heiko Wersing, Dorothea Kolossa. 341-353 [doi]
- DNN-Based Semantic Rescoring Models for Speech RecognitionIrina Illina, Dominique Fohr. 357-370 [doi]
- Identification of Scandinavian Languages from Speech Using Bottleneck Features and X-VectorsPetr Cerva, Lukás Mateju, Frantisek Kynych, Jindrich Zdánský, Jan Nouza. 371-381 [doi]
- LSTM-XL: Attention Enhanced Long-Term Memory for LSTM CellsTamás Grósz, Mikko Kurimo. 382-393 [doi]
- Improving RNN-T ASR Performance with Date-Time and Location AwarenessSwayambhu Nath Ray, Soumyajit Mitra, Raghavendra Bilgi, Sri Garimella. 394-404 [doi]
- BrAgriSpeech: A Corpus of Brazilian-Portuguese Agricultural Reported SpeechBrett Drury, Samuel Morais Drury. 405-412 [doi]
- Exploiting Large-Scale Teacher-Student Training for On-Device Acoustic ModelsJing Liu, Rupak Vignesh Swaminathan, Sree Hari Krishnan Parthasarathi, Chunchuan Lyu, Athanasios Mouchtaris, Siegfried Kunzmann. 413-424 [doi]
- An AI-Based Detection System for Mudrabharati: A Novel Unified Fingerspelling System for Indic ScriptsF. Amal Jude Ashwin, V. Srinivasa Chakravarthy, Sunil Kumar Kopparapu. 425-434 [doi]
- Is There Any Additional Information in a Neural Network Trained for Pathological Speech Classification?Cristian D. Rios-Urrego, Juan Camilo Vásquez-Correa, Juan Rafael Orozco-Arroyave, Elmar Nöth. 435-447 [doi]
- On Comparison of XGBoost and Convolutional Neural Networks for Glottal Closure Instant DetectionMichal Vrastil, Jindrich Matousek. 448-456 [doi]
- Emotional State Modeling for the Assessment of Depression in Parkinson's DiseasePaula Andrea Pérez-Toro, Juan Camilo Vásquez-Correa, Tomás Arias-Vergara, Philipp Klumpp, Maria Schuster, Elmar Nöth, Juan Rafael Orozco-Arroyave. 457-468 [doi]
- Attention-Based End-to-End Named Entity Recognition from SpeechDejan Porjazovski, Juho Leinonen 0002, Mikko Kurimo. 469-480 [doi]
- Incorporation of Iterative Self-supervised Pre-training in the Creation of the ASR System for the Tatar LanguageAidar Khusainov, Dzhavdet Suleymanov, Ilnur Muhametzyanov. 481-488 [doi]
- Speakers Talking Foreign Languages in a Multi-lingual TTS SystemZdenek Hanzlícek, Jakub Vít, Markéta Rezácková. 489-498 [doi]
- Voice Activity Detection for Ultrasound-Based Silent Speech Interfaces Using Convolutional Neural NetworksAmin Honarmandi Shandiz, László Tóth 0001. 499-510 [doi]
- How Much End-to-End is Tacotron 2 End-to-End TTS SystemDaniel Tihelka, Jindrich Matousek, Alice Tihelková. 511-522 [doi]
- CNN-TDNN-Based Architecture for Speech Recognition Using Grapheme Models in Bilingual Czech-Slovak TaskJosef V. Psutka, Jan Svec, Ales Prazák. 523-533 [doi]
- A Multimodal Model for Predicting Conversational FeedbacksAuriane Boudin, Roxane Bertrand, Stéphane Rauzy, Magalie Ochs, Philippe Blache. 537-549 [doi]
- Estimating Social Distance Between Interlocutors with MFCC-Based Acoustic Models for VowelsPavel Kholiavin, Alla Menshikova, Tatiana Kachkovskaia, Daniil Kocharov. 550-557 [doi]
- Remote Learning of Speaking in Syntactic Forms with Robot-Avatar-Assisted Language Learning SystemTaisei Najima, Tsuneo Kato, Akihiro Tamura, Seiichi Yamamoto. 558-566 [doi]