Search Results for author:
Found 12 papers, 4 papers with code
Mitigating Heterogeneity among Factor Tensors via Lie Group Manifolds for Tensor Decomposition Based Temporal Knowledge Graph Embedding
Recent studies have highlighted the effectiveness of tensor decomposition methods in the Temporal Knowledge Graphs Embedding (TKGE) task.
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models
Subsequently, the retrieval model correlates new inputs with relevant guidelines, which guide LLMs in response generation to ensure safe and high-quality outputs, thereby aligning with human values.
Improving CTC-AED model with integrated-CTC and auxiliary loss regularization
Connectionist temporal classification (CTC) and attention-based encoder decoder (AED) joint training has been widely applied in automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation Rotation
This paper presents a translation-based knowledge geraph embedding method via efficient relation rotation (TransERR), a straightforward yet effective alternative to traditional translation-based knowledge graph embedding models.
Ranked #16 on
Link Property Prediction
on ogbl-wikikg2
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning
For the retriever, we adopt a number-aware negative sampling strategy to enable the retriever to be more discriminative on key numerical facts.
Ranked #1 on
Conversational Question Answering
on ConvFinQA
Coarse-to-Fine Recursive Speech Separation for Unknown Number of Speakers
This paper formulates the speech separation with the unknown number of speakers as a multi-pass source extraction problem and proposes a coarse-to-fine recursive speech separation method.
Incorporating Inner-word and Out-word Features for Mongolian Morphological Segmentation
The inner-word encoder uses the self-attention mechanisms to capture the inner-word features of the target word.
FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement
In our proposed FullSubNet, we connect a pure full-band model and a pure sub-band model sequentially and use practical joint training to integrate these two types of models' advantages.
UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Condition
This approach consists of a generator network and a discriminator network, which operate directly in the time domain.
An Edge Information and Mask Shrinking Based Image Inpainting Approach
The mask shrinking strategy is employed in the image completion model to track the areas to be repaired.
SNR-Based Teachers-Student Technique for Speech Enhancement
Specifically, this method consists of multiple teacher models and a student model.
Sub-Band Knowledge Distillation Framework for Speech Enhancement
In single-channel speech enhancement, methods based on full-band spectral features have been widely studied.
