Text, Speech, and Dialogue -

. .

Résumé :
.- Speech. .- Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR. .- An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training. .- Optimizing ASR Models with Semantic Information. .- Efficient Enhancement of Norwegian ASR Model. .- Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue. .- Audio&ndash...

Biographie:

.- Speech.

.- Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR.

.- An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training.

.- Optimizing ASR Models with Semantic Information.

.- Efficient Enhancement of Norwegian ASR Model.

.- Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue.

.- Audio&ndash...

Sommaire:
Vision Contrastive Learning for Phonological Class Recognition. .- TOSD-Net: A CNN-Transformer Architecture for Robust Frame-Level Overlapping Speech Detection in Diverse Acoustic Conditions. .- An Exploration of ECAPA-TDNN and x-vector Speaker Representations in Zero-shot Multi-speaker TTS. .- Emotion-Aware Speech-Driven Facial Avatar Animation via Joint Blendshape Prediction and Emotion Recognition. .- Beyond Static Emotions: Leveraging Multitask Learning to Model Dynamics of Dimensional Affect in Speech. .- Implicit Speaker Group Encoding in Self-supervised Speech Recognition Models. .- Combining Temporal Visual Dynamics and Audio Representations for Robust Speaker Identification. .- Sentences vs Phrases in Neural Speech Synthesis: the Phrases Strike Back. .- Evaluating Phoneme-Level Pretraining in Czech Text-to-Speech Synthesis. .- Unifying Global and Near-Context Biasing in a Single Trie Pass. .- Synthesising Cross-Speaker Data for Low-Resource Pathological Speech Recognition with PEFT. .- Multilingual Stutter Event Detection for English, German, and Mandarin Speech. .- How Far Can Synthetic Speech Go? Enhancing ASR in Low-Resource Scenarios via Voice Cloning. .- Enhancing Detection of Parkinson-induced Dysarthria with Cross-lingual Transfer Learning. .- Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks. .- Detection of Cognitive Disorders Using ASR-Based Nonsense Words Repetition. .- Mind the Gap: Entity-Preserved Context-Aware ASR for Structured Transcriptions. .- Boosting CTC-Based ASR Using LLM-Based Intermediate Loss Regularization. .- Robust Disfluency Labeling in Spontaneous Speech: Insights from Diverse Hungarian Corpora Including Mentally Ill Speakers. .- ParCzech4Speech: A New Speech Corpus Derived from Czech Parliamentary Data. .- Towards an Accurate Domain-Specific ASR: Transcription for Pathology. .- Automated Speaking Assessment for L2 Learners of Czech. .- Inclusive ASR for Critical Public Services: Debiasing with Actor-Simulated Speech. .- RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification. .- Systematic FAIRness Assessment of Open Voice Biomarker Datasets for Mental Health and Neurodegenerative Diseases. .- When Silence Speaks: Understanding Open-Ended Responses via LLMs in Therapeutic Voice Interaction. .- Multilingual Domain Adaptation for Speech Recognition Using LLMs. .- Using Cross-attention For Conversational ASR Over The Telephone....