Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Directional Source Separation for Robust Speech Recognition on Smart GlassesMeta · IEEE International Conference on Acoustics Speech and Signal Processing12 citationsMar 12, 2025Phoneme-Level Contrastive Learning for User-Defined Keyword Spotting with Flexible EnrollmentiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing12 citationsMar 12, 2025Efficient Streaming LLM for Speech RecognitionMeta · IEEE International Conference on Acoustics Speech and Signal Processing12 citationsMar 12, 2025Effective Integration of KAN for Keyword SpottingMeta · IEEE International Conference on Acoustics Speech and Signal Processing11 citationsMar 12, 2025MambaTrack: Exploiting Dual-Enhancement for Night UAV TrackingCloudWalk Technology · IEEE International Conference on Acoustics Speech and Signal Processing11 citationsMar 12, 2025Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and InferenceNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing11 citationsMar 12, 2025SimulTron: On-Device Simultaneous Speech to Speech TranslationAlphabet, Google DeepMind · IEEE International Conference on Acoustics Speech and Signal Processing10 citationsMar 12, 2025MVANet: Multi-Stage Video Attention Network for Sound Event Localization and Detection with Source Distance EstimationiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing10 citationsMar 12, 2025On the Limitations of Vision-Language Models in Understanding Image TransformsCohere · arXiv (Cornell University)9 citationsMar 12, 2025Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion ModelsAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing9 citationsMar 12, 2025EMMeTT: Efficient Multimodal Machine Translation TrainingNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing8 citationsMar 12, 2025Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-AttentioniFlytek · IEEE International Conference on Acoustics Speech and Signal Processing8 citationsMar 12, 2025MathReader : Text-to-Speech for Mathematical DocumentsNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing8 citationsMar 12, 2025Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and DatasetMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing8 citationsMar 12, 2025ComplexDec: A Domain-robust High-fidelity Neural Audio Codec with Complex Spectrum ModelingMeta · IEEE International Conference on Acoustics Speech and Signal Processing8 citationsMar 12, 2025Towards Sub-millisecond Latency Real-Time Speech Enhancement Models on HearablesAlphabet, Google DeepMind · IEEE International Conference on Acoustics Speech and Signal Processing7 citationsMar 12, 2025HiFi-SR: A Unified Generative Transformer-Convolutional Adversarial Network for High-Fidelity Speech Super-ResolutionAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing7 citationsMar 12, 2025CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language ModelsAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing7 citationsMar 12, 2025Incorporating Spatial Cues in Modular Speaker Diarization for Multi-channel Multi-party MeetingsiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing7 citationsMar 12, 2025Modifying Flow Matching for Generative Speech EnhancementNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing7 citationsMar 12, 2025LLM-Guided Compositional Program SynthesisMicrosoft · arXiv (Cornell University)6 citationsMar 12, 20253D Gaussian Splatting with Grouped Uncertainty for Unconstrained ImagesNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing6 citationsMar 12, 2025Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware DecodingMeta · IEEE International Conference on Acoustics Speech and Signal Processing6 citationsMar 12, 2025Ultra-Low Latency Speech Enhancement -A Comprehensive StudyMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing6 citationsMar 12, 2025Faster Speech-LLaMA Inference with Multi-token PredictionMeta · IEEE International Conference on Acoustics Speech and Signal Processing6 citationsMar 12, 2025