Showing 1–18 of 18 results
/ Date/ Name
Dec 7, 2018Nonlinear Conjugate Gradients For Scaling Synchronous Distributed DNN TrainingAug 5, 2020Hybrid Transformer/CTC Networks for Hardware Efficient Voice TriggeringOct 31, 2018Democratizing Production-Scale Distributed Deep LearningJun 13, 2024Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech DetectionApr 5, 2022Improving Voice Trigger Detection with Metric LearningMay 18, 2023PDP: Parameter-free Differentiable Pruning is All You NeedMay 20, 2023Efficient Multimodal Neural Networks for Trigger-less Voice AssistantsJul 8, 2025MMW: Side Talk Rejection Multi-Microphone Whisper on Smart GlassesSep 2, 2023eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language ModelsOct 23, 2023Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal FeaturesOct 9, 2023Streaming Anchor Loss: Augmenting Supervision with Temporal SignificanceMar 14, 2023R2 Loss: Range Restriction Loss for Model Compression and QuantizationAug 28, 2021DKM: Differentiable K-Means Clustering Layer for Neural Network CompressionMar 30, 2022Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised ModelsJun 12, 2024Comparative Analysis of Personalized Voice Activity Detection Systems: Assessing Real-World EffectivenessJan 25, 2020Lattice-based Improvements for Voice Triggering Using Graph Neural NetworksOct 28, 2024Device-Directed Speech Detection for Follow-up Conversations Using Large Language ModelsMay 14, 2021Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation