Speech & Audio

Pitfalls and Limits in Automatic Dementia Assessment Interspeech 2025 Playing with Voices: Tabletop Role-Playing Game Recordings as a Diarization Challenge NAACL 2025 Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extraction Interspeech 2025 PodAgent: A Comprehensive Framework for Podcast Generation ACL 2025 PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis AAAI 2025 PolyNorm: Few-Shot LLM-Based Text Normalization for Text-to-Speech EMNLP 2025 Power Spectral Density Estimation for Acoustic Source Separation Using A Spherical Microphone Array Interspeech 2025 PPGs-BERT: Leveraging Phoneme Sequence and BERT for Alzheimer’s Disease Detection from Spontaneous Speech Interspeech 2025 Pre-aspiration in Iceland Is Conditioned by Gender/Sex Interspeech 2025 Predicting Prosodic Boundaries for Children’s Texts EMNLP 2025 Prediction of listening effort ratings for habitual and clear-Lombard speech presented in noise Interspeech 2025 Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison NAACL 2025 Preserving Comorian Linguistic Heritage: Bidirectional Transliteration Between the Latin Alphabet and the Kamar-Eddine System NAACL 2025 Pretraining Multi-Speaker Identification for Neural Speaker Diarization Interspeech 2025 Privacy Preserving Data Selection for Bias Mitigation in Speech Models ACL 2025 Privacy-Preserving Speaker Verification via End-to-End Secure Representation Learning Interspeech 2025 Private kNN-VC: Interpretable Anonymization of Converted Speech Interspeech 2025 Proactive Hearing Assistants that Isolate Egocentric Conversations EMNLP 2025 ProBiEM: Acoustic and Lexical Correlates of Prosodic Prominence in English-Malayalam Bilingual Speech Interspeech 2025 Probing Prosodic Differences Between Two Regional Varieties of Brazilian Portuguese Interspeech 2025 Probing the Robustness Properties of Neural Speech Codecs Interspeech 2025 Prolongation in Romanian Interspeech 2025 ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs Interspeech 2025 PromptEVC: Controllable Emotional Voice Conversion with Natural Language Prompts Interspeech 2025 Prompting Whisper for Improved Verbatim Transcription and End-to-end Miscue Detection Interspeech 2025