Speech & Audio

Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation AAAI 2025 Large Language Models based ASR Error Correction for Child Conversations Interspeech 2025 LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention Interspeech 2025 LATE: Open Source Toolkit for Latvian and Latgalian Speech Transcription Interspeech 2025 Layer-Wise Decision Fusion for Fake Audio Detection Using XLS-R Interspeech 2025 Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations EMNLP 2025 Learning More with Less: Self-Supervised Approaches forLow-Resource Speech Emotion Recognition Interspeech 2025 Learning Optimal Prosody Embedding Codebook based on F0 and Energy Interspeech 2025 Learning Phonetic Context-Dependent Viseme for Enhancing Speech-Driven 3D Facial Animation Interspeech 2025 Learning to Highlight Audio by Watching Movies CVPR 2025 Learning to See through Sound: From VggCaps to Multi2Cap for Richer Automated Audio Captioning EMNLP 2025 Legally validated evaluation framework for voice anonymization Interspeech 2025 LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors EMNLP 2025 Length Aware Speech Translation for Video Dubbing Interspeech 2025 Lessons Learned from the URGENT 2024 Speech Enhancement Challenge Interspeech 2025 Lessons Learnt: Revisit Key Training Strategies for Effective Speech Emotion Recognition in the Wild Interspeech 2025 Let’s Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR ACL 2025 Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions ICLR 2025 Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment NAACL 2025 Leveraging AM and FM Rhythm Spectrograms for Dementia Classification and Assessment Interspeech 2025 Leveraging Artificial Intelligence to Bridge Gaps in Pediatric Oncology Care for Marginalized Spanish-Speaking Communities IJCAI 2025 Leveraging Geographic Metadata for Dialect-Aware Speech Recognition Interspeech 2025 Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection Interspeech 2025 Leveraging Large Language Models for Spontaneous Speech-Based Suicide Risk Detection Interspeech 2025 Leveraging Large Pre-trained Multilingual Models for High-Quality Speech-to-Text Translation on Industry Scenarios COLING 2025