Text, Speech, and Dialogue: 26th International Conference, Tsd 2023, Pilsen, Czech Republic, September 4-6, 2023, Proceedings

ISBN-13: 9783031404979 / Angielski

Kamil Ekstein; Frantisek Pártl; Miloslav Konopík

Spis treści

​Text: Japanese How-to Tip Machine Reading Comprehension by Multi-task Learning based on Generative Model.- One model to rule them all: ranking Slovene summarizers.- Searching for Reasons of Transformers’ Success: Memorization vs Generalization.- A Dataset and Strong Baselines for Classification of Czech News Texts.- Resolving Hungarian Anaphora with ChatGPT.- Advancing Hungarian Text Processing with HuSpaCy: Efficient and Accurate NLP Pipelines.- ParaDiom - A Parallel Corpus of Idiomatic Texts.- Measuring Sentiment Bias in Machine Translation.- Mono- and multilingual GPT-3 models for Hungarian.- The Unbearable Lightness of Morph Classification.- A German Parallel Clausal Coordinate Ellipsis Corpus that Aligns Sentences from the TüBa-D/Z Treebank with Reconstructed Canonical Forms.- Speech: Identifying Subjects Wearing a Mask from the Speech by Means of Encoded Speech Representations.- Impact of Including Pathological Speech in Pre-Training on Pathology Detection.- Morphological Tagging and Lemmatization of Spoken Corpora of Czech.- HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics.- Online Speaker Diarization Using Optimized SE-ResNet Architecture.- CML-TTS: A Multilingual Dataset for Speech Synthesis in Low-Resource Languages (Speech (in general), Corpora and Language Resources, Spe.- Developing State-of-the-Art End-to-End ASR for Norwegian.- VITS: Quality vs. Speed Analysis.- When Whisper Meets TTS: Domain Adaptation Using Only Synthetic Speech Data.- Unsupervised Learning for Automatic Speech Recognition In Air Traffic Control Environment.- The Effect of Human-Likeliness in French Robot-Directed Speech: A Study of Speech Rate and Fluency.- An online diarization approach for streaming applications based on tree-clustering and Bayesian resegmentation.- Evaluation of Speech Representations for MOS prediction.- Unified Modeling of Multi-Domain Multi-Device ASR Systems.- Voice Cloning for Voice Disorders: Impact of Phonetic Content.- Towards End-to-end Speech-to-text Summarization.- Multilingual TTS Accent Impressions for Accented ASR.- Transfer Learning of Transformer-based Speech Recognition Models from Czech to Slovak.- Automatic Pronunciation Assessment of Non-native English based on Phonological Analysis.- Language Generalization using Active Learning in the context of Parkinson’s Disease Classification.