Search Results for author:
Found 10 papers, 6 papers with code
MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition
In this paper, we aim to learn the shared representations across modalities to bridge their gap.
Towards Balanced Active Learning for Multimodal Classification
Our studies demonstrate that the proposed method achieves more balanced multimodal learning by avoiding greedy sample selection from the dominant modality.
UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning
Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks.
Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition
However, most existing AVSR approaches simply fuse the audio and visual features by concatenation, without explicit interactions to capture the deep correlations between them, which results in sub-optimal multimodal representations for downstream speech recognition task.
Audio-Visual Speech Recognition
Automatic Speech Recognition
+3
Unsupervised Noise adaptation using Data Simulation
Deep neural network based speech enhancement approaches aim to learn a noisy-to-clean transformation using a supervised learning paradigm.
Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation
To alleviate this problem, we propose a novel network to unify speech enhancement and separation with gradient modulation to improve noise-robustness.
Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning
Audio-visual speech recognition (AVSR) has gained remarkable success for ameliorating the noise-robustness of speech recognition.
Self-critical Sequence Training for Automatic Speech Recognition
Although automatic speech recognition (ASR) task has gained remarkable success by sequence-to-sequence models, there are two main mismatches between its training and testing that might lead to performance degradation: 1) The typically used cross-entropy criterion aims to maximize log-likelihood of the training data, while the performance is evaluated by word error rate (WER), not log-likelihood; 2) The teacher-forcing method leads to the dependence on ground truth during training, which means that model has never been exposed to its own prediction before testing.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information
In this paper, we propose an end-to-end speech emotion recognition system using multi-level acoustic information with a newly designed co-attention module.
Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning
Automated Audio captioning (AAC) is a cross-modal task that generates natural language to describe the content of input audio.
