Full Description
This book constitutes the refereed proceedings of the 26th International Conference on Text, Speech, and Dialogue, TSD 2023, held in Pilsen, Czech Republic, during September 4-6, 2023.
The 31 full papers presented together with the abstracts of 3 keynote talks were carefully reviewed and selected from 64 submissions. The conference attracts researchers not only from Central and Eastern Europe but also from other parts of the world. One of its goals has always been bringing together NLP researchers with various interests from different parts of the world and promoting their cooperation. One of the ambitions of the conference is, not only to deal with dialogue systems but also to improve dialogue among researchers in areas of NLP, i.e., among the "text" and the "speech" and the "dialogue" people.
Contents
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 ofSpeech 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.
