Speech & Audio

What the Filler? Both ASR Systems and Humans Struggle More With Other Kinds of Disfluencies Than With Filler Particles Interspeech 2025 When focus shapes the flow: prosodic restructuring in Mandarin complex nominals Interspeech 2025 When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds Interspeech 2025 When The MOS Predictor Asks For Training Annotation In Cross Lingual/Domain Adaptation Interspeech 2025 Whilter: A Whisper-based Data Filter for "In-the-Wild" Speech Corpora Using Utterance-level Multi-Task Classification Interspeech 2025 Whisper-Based Multilingual Alzheimer's Disease Detection and Improvements for Low-Resource Language Interspeech 2025 WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper Interspeech 2025 Whispering in Ol Chiki: Cross-Lingual Transfer Learning for Santali Speech Recognition IJCNLP 2025 WhisperMSS: A Two-Stage Framework for Mandarin Singing Transcription and Segmentation Using Pretrained Models Interspeech 2025 WhiStress: Enriching Transcriptions with Sentence Stress Detection Interspeech 2025 Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM Interspeech 2025 Who knows best? Effects of speech disfluencies on incentivized decision-making Interspeech 2025 Why is children's ASR so difficult? Analyzing children's phonological error patterns using SSL-based phoneme recognizers Interspeech 2025 WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection Interspeech 2025 Word-Level Error Analysis in Decoding Systems: From Speech Recognition to Brain-Computer Interfaces Interspeech 2025 Word Level Timestamp Generation for Automatic Speech Recognition and Translation Interspeech 2025 Word stress in self-supervised speech models: A cross-linguistic comparison Interspeech 2025 WTFormer: A Wavelet Conformer Network for MIMO Speech Enhancement with Spatial Cues Peservation Interspeech 2025 X-ARES: A Comprehensive Framework for Assessing Audio Encoder Performance Interspeech 2025 XAttnMark: Learning Robust Audio Watermarking with Cross-Attention ICML 2025 xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement Interspeech 2025 YodiV3: NLP for Togolese Languages with Eyaa-Tom Dataset and the Lom Metric ACL 2025 You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks Interspeech 2025 Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations ICCV 2025 Zero-Shot Learning for Acoustic Event Classification Using an Attribute Vector and Conditional GAN Interspeech 2025