Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Slide FFT on a homogeneous mesh in wafer-scale computingCerebras Systems · Discover Computing2 citationsMar 12, 2025THE EVOLUTION OF SELF-HEALING INFRASTRUCTURE: AI-DRIVEN AUTOMATION IN MODERN DEVOPSNVIDIA · INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY AND MANAGEMENT INFORMATION SYSTEMS1 citationMar 12, 2025Easing Optimization Paths: a Circuit PerspectiveMeta · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Spatial-Temporal Reconstruction Error for AIGC-based Forgery Image DetectionAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Graph Pooling via Dropping Task-Irrelevant NodesSenseTime · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Audio Diffusion with Large Language ModelsAlphabet · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025SiMBA-TS: Simplified Channel Mixing and Mamba for Long-term Time Series ForecastingMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Make Some Noise: Towards LLM audio reasoning and generation using sound tokensMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Speech Re-Painting for Robust ASRAlphabet · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Speech Separation for Low-Resource LanguagesAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Predicting Compact Phrasal Rewrites with Large Language Models for ASR Post EditingAlphabet · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Robust Speech Recognition with Schrödinger Bridge-Based Speech EnhancementNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Reexamining the Efficacy of MetricGAN for Speech EnhancementMeta · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Target word activity detector: An approach to obtain ASR word boundaries without lexiconMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Impairments are Clustered in Latents of Deep Neural Network-based Speech Quality ModelsAlphabet · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Reliable Imputed-Sample Assisted Vertical Federated LearningAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing1 citationMar 12, 2025Ordered Semantically Diverse Sampling for Textual DataMicrosoft · arXiv (Cornell University)Mar 12, 2025Weak-to-Strong Generalization in Speech RecognitionAlphabet · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Self-supervised Prosody Learning at Phoneme-level with Momentum Contrast for Speech SynthesisiFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025A New Model for Prototype-based Continual Learning in Hyperspherical SpaceAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Exploring Inter-Variate and Long-Term Dependencies to Boost Multivariate Time Series ForecastingAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Efficient Quality Controllable Neural Image Compression based on QD-ModelAlibaba · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Leveraging Boolean Directivity Embedding for Binaural Target Speaker ExtractioniFlytek · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025Speech-N-LlaMA: Improving Speech LLMs with Multi-Pass TrainingMeta · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025LIMMITS’25: Multilingual Streaming TTS With Neural Codecs for Indian LanguagesMicrosoft · IEEE International Conference on Acoustics Speech and Signal ProcessingMar 12, 2025