Speech & Audio

LLM-based phoneme-to-grapheme for phoneme-based speech recognition Interspeech 2025 LLM ContextBridge: A Hybrid Approach for Intent and Dialogue Understanding in IVSR COLING 2025 LLM-Synth4KWS: Scalable Automatic Generation and Synthesis of Confusable Data for Custom Keyword Spotting Interspeech 2025 LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM ACL 2025 Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models ACL 2025 Location-Aware Target Speaker Extraction for Hearing Aids Interspeech 2025 LombardTokenizer: Disentanglement and Control of Vocal Effort in a Neural Speech Codec Interspeech 2025 Long-Context Speech Synthesis with Context-Aware Memory Interspeech 2025 Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use Interspeech 2025 Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models ACL 2025 Low Complex IIR Adaptive Hear-Through Ambient Filtering for Overcoming Practical Constraints in Earbuds Interspeech 2025 LRBA: Stealthy Backdoor Attacks on Speech Classification via Latent Rearrangement in VITS Interspeech 2025 LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec Interspeech 2025 LSPnet: an ultra-low bitrate hybrid neural codec Interspeech 2025 M3Net: Efficient Time-Frequency Integration Network with Mirror Attention for Audio Classification on Edge AAAI 2025 MAD Speech: Measures of Acoustic Diversity of Speech NAACL 2025 MADUV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge Interspeech 2025 Mamba-based Hybrid Model for Speech Enhancement Interspeech 2025 ManaTTS Persian: a recipe for creating TTS datasets for lower resource languages NAACL 2025 MASV: Speaker Verification with Global and Local Context Mamba Interspeech 2025 MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula AAAI 2025 MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation ICCV 2025 MDDM: A Multi-view Discriminative Enhanced Diffusion-based Model for Speech Enhancement Interspeech 2025 Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks ACL 2025 Medusa: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions Interspeech 2025