Search Results for author:
Found 24 papers, 6 papers with code
SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG
Decoding speech from brain signals is a challenging research problem that holds significant importance for studying speech processing in the brain.
Region-Based Optimization in Continual Learning for Audio Deepfake Detection
To address this issue, we propose a continual learning method named Region-Based Optimization (RegO) for audio deepfake detection.
DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection
To address these issues, this paper proposes a dual attention refinement network with spatiotemporal construction for AAD, named DARNet, which consists of the spatiotemporal construction module, dual attention refinement module, and feature fusion \& classifier module.
Mitigating Gender Bias in Code Large Language Models via Model Editing
At the same time, the experimental results show that, considering both the gender bias of the model and its general code generation capability, MG-Editing is most effective when applied at the row and neuron levels of granularity.
LiSenNet: Lightweight Sub-band and Dual-Path Modeling for Real-Time Speech Enhancement
Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility.
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
While large language models (LLMs) excel in many domains, their complexity and scale challenge deployment in resource-limited environments.
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models
In order to answer this question, we propose the UNO Arena based on the card game UNO to evaluate the sequential decision-making capability of LLMs and explain in detail why we choose UNO.
Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion
This paper proposes a progressive distillation method based on masked generation features for KGC task, aiming to significantly reduce the complexity of pre-trained models.
DGSD: Dynamical Graph Self-Distillation for EEG-Based Auditory Spatial Attention Detection
Specifically, to effectively represent the non-Euclidean properties of EEG signals, dynamical graph convolutional networks are applied to represent the graph structure of EEG signals, which can also extract crucial features related to auditory spatial attention in EEG signals.
Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection
The main purpose of this system is to improve the model's ability to learn precise forgery information for FSD task in low-quality scenarios.
Learning From Yourself: A Self-Distillation Method for Fake Speech Detection
To address this problem, we propose using the deepest network instruct shallow network for enhancing shallow networks.
SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detection
Some scene fake audio detection benchmark results on the SceneFake dataset are reported in this paper.
Fully Automated End-to-End Fake Audio Detection
The existing fake audio detection systems often rely on expert experience to design the acoustic features or manually design the hyperparameters of the network structure.
Audio Deepfake Detection Based on a Combination of F0 Information and Real Plus Imaginary Spectrogram Features
Meanwhile, to make full use of the phase and full-band information, we also propose to use real and imaginary spectrogram features as complementary input features and model the disjoint subbands separately.
ADD 2022: the First Audio Deep Synthesis Detection Challenge
Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021.
MS-MDA: Multisource Marginal Distribution Adaptation for Cross-subject and Cross-session EEG Emotion Recognition
Although several studies have adopted domain adaptation (DA) approaches to tackle this problem, most of them treat multiple EEG data from different subjects and sessions together as a single source domain for transfer, which either fails to satisfy the assumption of domain adaptation that the source has a certain marginal distribution, or increases the difficulty of adaptation.
Deep Time Delay Neural Network for Speech Enhancement with Full Data Learning
This paper proposes a deep time delay neural network (TDNN) for speech enhancement with full data learning.
Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition
The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Deep imitator: Handwriting calligraphy imitation via deep attention networks
Calligraphy imitation (CI) from a handful of target handwriting samples is such a challenging task that most of the existing writing style analysis or handwriting generation methods do not exhibit satisfactory performance.
Simultaneous Denoising and Dereverberation Using Deep Embedding Features
In this paper, we propose a joint training method for simultaneous speech denoising and dereverberation using deep embedding features, which is based on the deep clustering (DC).
Adversarial Transfer Learning for Punctuation Restoration
The other is that POS tags are provided by an external POS tagger.
Deep Attention Fusion Feature for Speech Separation with End-to-End Post-filter Method
Secondly, to pay more attention to the outputs of the pre-separation stage, an attention module is applied to acquire deep attention fusion features, which are extracted by computing the similarity between the mixture and the pre-separated speech.
Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features
Specifically, we apply the deep clustering network to extract deep embedding features.
Discriminative Learning for Monaural Speech Separation Using Deep Embedding Features
Firstly, a DC network is trained to extract deep embedding features, which contain each source's information and have an advantage in discriminating each target speakers.
