Text, Speech, and Dialogue: 27th International Conference, TSD 2024, Brno, Czech Republic, September 9–13, 2024, Proceedings, Part II(Lecture Notes in Artificial Intelligence)

The two-volume set LNAI 15048 and 15049 constitutes the refereed proceedings of the 27th International Conference on Text, Speech, and Dialogue, TSD 2024, held in Brno, Czech Republic, during September 9–13, 2024. The 50 revised full papers presented in these deadline proceedings were carefully reviewed and selected from 103 submissions.  The papers are organized in the following topical sections: Part I: Text Part II: Speech, Dialogue

Table of Contents:
.- Speech. .- Retrieval Augmented Spoken Language Generation for Transport Domain. .- Adapting Audiovisual Speech Synthesis to Estonian. .- Dysphonia Diagnosis Using Self-Supervised Speech Models in Mono- and Cross-Lingual Settings. .- Sentences vs Phrases in Neural Speech Synthesis. .- Zero-Shot vs. Few-Shot Multi-Speaker TTS Using Pre-trained Czech SpeechT5 Model. .- Deep Speaker Embeddings for Speaker Verification of Children. .- Improved Alignment for Score Combination of RNN-T and CTC Decoder for Online Decoding. .- Attention to Phonetics: A Visually Informed Explanation of Speech Transformers. .- Effects of Training Strategies and the Amount of Speech Data on the Quality of Speech Synthesis. .- Stream-Based Active Learning for Speech Emotion Recognition via Hybrid Data Selection and Continuous Learning. .- Data Alignment and Duration Modelling in VITS. .- Multiword Expressions Resources for Italian: Presenting a Manually Annotated Spoken Corpus. .- Generating High-Quality F0 Embeddings Using the Vector-Quantized Variational Autoencoder. .- Anonymizing Dysarthric Speech: Investigating the Effects of Voice Conversion on Pathological Information Preservation. .- X-vector-based Speaker Diarization Using Bi-LSTM and Interim Voting-driven Post-processing. .- A Paradigm for Interpreting Metrics and Measuring Error Severity in Automatic Speech Recognition. .- Enhancing Speech Emotion Recognition Using Transfer Learning From Speaker Embeddings. .- Dialogue. .- Investigating Low-Cost LLM Annotation for Spoken Dialogue Understanding Datasets. .- PiCo-VITS: Leveraging Pitch Contours for Fine-grained Emotional Speech Synthesis. .- Improving and Understanding Clarifying Question Generation in Conversational Search. .- Explainable Multimodal Fusion for Dementia Detection From Text and Speech. .- Robust Classification of Parkinson’s Speech: an Approximation to a Scenario With Non-controlled Acoustic Conditions. .- Leveraging Conceptual Similarities to Enhance Modeling of Factors Affecting Adolescents’ Well-Being. .- Joint-Average Mean and Variance Feature Matching (JAMVFM) Semi-supervised GAN with Additional-Objective Training Function for Intent Detection. .- Capturing Task-Related Information for Text-Based Grasp Classification Using Fine-Tuned Embeddings. .- StepDP: A Step Towards Expressive and Pervasive Dialogue Platforms . .- Automatic Classification of Parkinson’s Disease Using Wav2vec Embeddings at Phoneme, Syllable, and Word Levels.