Multimodal large language models have become a popular topic in deep visual understanding due to many promising real-world applications. However, hour-long video understanding, spanning over one hour and containing tens of thousands of visual frames, remains under-explored because of 1) challenging long-term video analyses, 2) inefficient large-model approaches, and 3) lack of large-scale benchmark datasets. Among them, in this paper, we focus on building a large-scale hour-long long video benchmark, HLV-1K1, designed to evaluate long video understanding models. HLV-1K comprises 1009 hour-long videos with 14,847 high-quality question answering (QA) and multi-choice question asnwering (MCQA) pairs with time-aware query and diverse annotations, covering frame-level, within-event-level, cross-event-level, and long-term reasoning tasks. We evaluate our benchmark using existing state-of-the-art methods and demonstrate its value for testing deep long video understanding capabilities at different levels and for various tasks. This includes promoting future long video understanding tasks at a granular level, such as deep understanding of long live videos, meeting recordings, and movies.

Multilingual speech emotion recognition aims to estimate a speaker’s emotional state using a contactless method across different languages. However, variability in voice characteristics and linguistic diversity poses significant challenges for zero-shot speech emotion recognition, especially with multilingual datasets. In this paper, we propose leveraging contrastive learning to refine multilingual speech features and extend large language models for zero-shot multilingual speech emotion estimation. Specifically, we employ a novel two-stage training framework to align speech signals with linguistic features in the emotional space, capturing both emotion-aware and language-agnostic speech representations. To advance research in this field, we introduce a large-scale synthetic multilingual speech emotion dataset, M5SER. Our experiments demonstrate the effectiveness of the proposed method in both speech emotion recognition and zero-shot multilingual speech emotion recognition, including previously unseen datasets and languages. Our introduced dataset and related code will be available on GitHub1.

Audio-visual deepfake detection scrutinizes manipulations in public video using complementary multimodal cues. Current methods, which train on fused multimodal data for multimodal targets face challenges due to uncertainties and inconsistencies in learned representations caused by independent modality manipulations in deepfake videos. To address this, we propose cross-modality and within-modality regularization to preserve modality distinctions during multimodal representation learning. Our approach includes an audio-visual transformer module for modality correspondence and a cross-modality regularization module to align paired audio-visual signals, preserving modality distinctions. Simultaneously, a within-modality regularization module refines unimodal representations with modality-specific targets to retain modal-specific details. Experimental results on the public audio-visual dataset, FakeAVCeleb, demonstrate the effectiveness and competitiveness of our approach.

Audio-visual speech recognition (AVSR) has gained remarkable success for ameliorating the noise-robustness of speech recognition. Mainstream methods focus on fusing audio and visual inputs to obtain modality-invariant representations. However, such representations are prone to over-reliance on audio modality as it is much easier to recognize than video modality in clean conditions. As a result, the AVSR model underestimates the importance of visual stream in face of noise corruption. To this end, we leverage visual modality-specific representations to provide stable complementary information for the AVSR task. Specifically, we propose a reinforcement learning (RL) based framework called MSRL, where the agent dynamically harmonizes modality-invariant and modality-specific representations in the auto-regressive decoding process. We customize a reward function directly related to task-specific metrics (i.e., word error rate), which encourages the MSRL to effectively explore the optimal integration strategy. Experimental results on the LRS3 dataset show that the proposed method achieves state-of-the-art in both clean and various noisy conditions. Furthermore, we demonstrate the better generality of MSRL system than other baselines when test set contains unseen noises.

Audio-visual speech recognition (AVSR) attracts a surge of research interest recently by leveraging multimodal signals to understand human speech.Mainstream approaches addressing this task have developed sophisticated architectures and techniques for multi-modality fusion and representation learning.However, the natural heterogeneity of different modalities causes distribution gap between their representations, making it challenging to fuse them.In this paper, we aim to learn the shared representations across modalities to bridge their gap.Different from existing similar methods on other multimodal tasks like sentiment analysis, we focus on the temporal contextual dependencies considering the sequence-to-sequence task setting of AVSR.In particular, we propose an adversarial network to refine framelevel modality-invariant representations (MIR-GAN), which captures the commonality across modalities to ease the subsequent multimodal fusion process.Extensive experiments on public benchmarks LRS3 and LRS2 show that our approach outperforms the state-of-the-arts 1 .

Deep neural network based speech enhancement approaches aim to learn a noisy-to-clean transformation using a supervised learning paradigm. However, such a trained-well transformation is vulnerable to unseen noises that are not included in training set. In this work, we focus on the unsupervised noise adaptation problem in speech enhancement, where the ground truth of target domain data is completely unavailable. Specifically, we propose a generative adversarial network based method to efficiently learn a converse clean-to-noisy transformation using a few minutes of unpaired target domain data. Then this transformation is utilized to generate sufficient simulated data for domain adaptation of the enhancement model. Experimental results show that our method effectively mitigates the domain mismatch between training and test sets, and surpasses the best baseline by a large margin.

Recent studies in neural network-based monaural speech separation (SS) have achieved a remarkable success thanks to increasing ability of long sequence modeling. However, they would degrade significantly when put under realistic noisy conditions, as the background noise could be mistaken for speaker’s speech and thus interfere with the separated sources. To alleviate this problem, we propose a novel network to unify speech enhancement and separation with gradient modulation to improve noise-robustness. Specifically, we first build a unified network by combining speech enhancement (SE) and separation modules, with multi-task learning for optimization, where SE is supervised by parallel clean mixture to reduce noise for downstream speech separation. Furthermore, in order to avoid suppressing valid speaker information when reducing noise, we propose a gradient modulation (GM) strategy to harmonize the SE and SS tasks from optimization view. Experimental results show that our approach achieves the state-of-the-art on large-scale Libri2Mix- and Libri3Mix-noisy datasets, with SI-SNRi results of 16.0 dB and 15.8 dB respectively. Our code is available at GitHub1.

Audio-visual speech recognition (AVSR) research has gained a great success recently by improving the noise-robustness of audio-only automatic speech recognition (ASR) with noise-invariant visual information. 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. In this paper, we propose a cross-modal global interaction and local alignment (GILA) approach for AVSR, which captures the deep audio-visual (A-V) correlations from both global and local perspectives. Specifically, we design a global interaction model to capture the A-V complementary relationship on modality level, as well as a local alignment approach to model the A-V temporal consistency on frame level. Such a holistic view of cross-modal correlations enable better multimodal representations for AVSR. Experiments on public benchmarks LRS3 and LRS2 show that our GILA outperforms the supervised learning state-of-the-art. Code is at https://github.com/YUCHEN005/GILA.

Training multimodal networks requires a vast amount of data due to their larger parameter space compared to unimodal networks. Active learning is a widely used technique for reducing data annotation costs by selecting only those samples that could contribute to improving model performance. However, current active learning strategies are mostly designed for unimodal tasks, and when applied to multimodal data, they often result in biased sample selection from the dominant modality. This unfairness hinders balanced multimodal learning, which is crucial for achieving optimal performance. To address this issue, we propose three guidelines for designing a more balanced multimodal active learning strategy. Following these guidelines, a novel approach is proposed to achieve more fair data selection by modulating the gradient embedding with the dominance degree among modalities. Our studies demonstrate that the proposed method achieves more balanced multimodal learning by avoiding greedy sample selection from the dominant modality. Our approach outperforms existing active learning strategies on a variety of multimodal classification tasks. Overall, our work highlights the importance of balancing sample selection in multimodal active learning and provides a practical solution for achieving more balanced active learning for multimodal classification.

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. In this paper, we propose an optimization method called self-critical sequence training (SCST) to make the training procedure much closer to the testing phase. As a reinforcement learning (RL) based method, SCST utilizes a customized reward function to associate the training criterion and WER. Furthermore, it removes the reliance on teacher-forcing and harmonizes the model with respect to its inference procedure. We conducted experiments on both clean and noisy speech datasets, and the results show that the proposed SCST respectively achieves 8.7% and 7.8% relative improvements over the baseline in terms of WER.

Speech Emotion Recognition (SER) aims to help the machine to understand human’s subjective emotion from only audio in-formation. However, extracting and utilizing comprehensive in-depth audio information is still a challenging task. 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. We firstly extract multi-level acoustic information, including MFCC, spectrogram, and the embedded high-level acoustic information with CNN, BiL-STM and wav2vec2, respectively. Then these extracted features are treated as multimodal inputs and fused by the pro-posed co-attention mechanism. Experiments are carried on the IEMOCAP dataset, and our model achieves competitive performance with two different speaker-independent cross-validation strategies. Our code is available on GitHub.

Reconstructing photorealistic multi-view images from an image with an arbitrary view has a wide range of applications in the field of face generation. However, most current pixel-based generation models cannot generate sufficiently realistic enough images. To address this problem, we propose an edge-conditioned multi-view image generation model called Edge-GAN. Edge-GAN utilizes edge information to guide the image generation based on the perspective of the target view while the details of the input image are used to influence the target image. Edge-GAN combines the input image with the target pose information to generate a coarse image with an approximate target outline which is then refined to a better quality using adversanal training. Experiments conducted show that our Edge-GAN is able to generate high-quality images of people with convincing details.