for the ALFA study
Abstract:Current movie dubbing technology can generate the desired voice from a given speech prompt, ensuring good synchronization between speech and visuals while accurately conveying the intended emotions. However, in movie dubbing, key aspects such as adapting to different dubbing styles, handling dialogue, narration, and monologue effectively, and understanding subtle details like the age and gender of speakers, have not been well studied. To address this challenge, we propose a framework of multi-modal large language model. First, it utilizes multimodal Chain-of-Thought (CoT) reasoning methods on visual inputs to understand dubbing styles and fine-grained attributes. Second, it generates high-quality dubbing through large speech generation models, guided by multimodal conditions. Additionally, we have developed a movie dubbing dataset with CoT annotations. The evaluation results demonstrate a performance improvement over state-of-the-art methods across multiple datasets. In particular, for the evaluation metrics, the SPK-SIM and EMO-SIM increases from 82.48% to 89.74%, 66.24% to 78.88% for dubbing setting 2.0 on V2C Animation dataset, LSE-D and MCD-SL decreases from 14.79 to 14.63, 5.24 to 4.74 for dubbing setting 2.0 on Grid dataset, SPK-SIM increases from 64.03 to 83.42 and WER decreases from 52.69% to 23.20% for initial reasoning setting on proposed CoT-Movie-Dubbing dataset in the comparison with the state-of-the art models.
Abstract:Currently, high-quality, synchronized audio is synthesized using various multi-modal joint learning frameworks, leveraging video and optional text inputs. In the video-to-audio benchmarks, video-to-audio quality, semantic alignment, and audio-visual synchronization are effectively achieved. However, in real-world scenarios, speech and audio often coexist in videos simultaneously, and the end-to-end generation of synchronous speech and audio given video and text conditions are not well studied. Therefore, we propose an end-to-end multi-modal generation framework that simultaneously produces speech and audio based on video and text conditions. Furthermore, the advantages of video-to-audio (V2A) models for generating speech from videos remain unclear. The proposed framework, DeepAudio, consists of a video-to-audio (V2A) module, a text-to-speech (TTS) module, and a dynamic mixture of modality fusion (MoF) module. In the evaluation, the proposed end-to-end framework achieves state-of-the-art performance on the video-audio benchmark, video-speech benchmark, and text-speech benchmark. In detail, our framework achieves comparable results in the comparison with state-of-the-art models for the video-audio and text-speech benchmarks, and surpassing state-of-the-art models in the video-speech benchmark, with WER 16.57% to 3.15% (+80.99%), SPK-SIM 78.30% to 89.38% (+14.15%), EMO-SIM 66.24% to 75.56% (+14.07%), MCD 8.59 to 7.98 (+7.10%), MCD SL 11.05 to 9.40 (+14.93%) across a variety of dubbing settings.
Abstract:Currently, high-quality, synchronized audio is synthesized from video and optional text inputs using various multi-modal joint learning frameworks. However, the precise alignment between the visual and generated audio domains remains far from satisfactory. One key factor is the lack of sufficient temporal and semantic alignment annotations in open-source video-audio and text-audio benchmarks. Therefore, we propose a framework for audio generation from videos, leveraging the internal chain-of-thought (CoT) of a multi-modal large language model (MLLM) to enable step-by-step reasoning without requiring additional annotations. Additionally, a corresponding multi-modal reasoning dataset is constructed to facilitate the learning of initial reasoning in audio generation. In the experiments, we demonstrate the effectiveness of the proposed framework in reducing misalignment (voice-over) in generated audio and achieving competitive performance compared to various state-of-the-art models. The evaluation results show that the proposed method outperforms state-of-the-art approaches across multiple metrics. Specifically, the F DP aSST indicator is reduced by up to 10.07%, the F DP AN N s indicator by up to 11.62%, and the F DV GG indicator by up to 38.61%. Furthermore, the IS indicator improves by up to 4.95%, the IB-score indicator increases by up to 6.39%, and the DeSync indicator is reduced by up to 0.89%.
Abstract:Creating high-quality sound effects from videos and text prompts requires precise alignment between visual and audio domains, both semantically and temporally, along with step-by-step guidance for professional audio generation. However, current state-of-the-art video-guided audio generation models often fall short of producing high-quality audio for both general and specialized use cases. To address this challenge, we introduce a multi-stage, multi-modal, end-to-end generative framework with Chain-of-Thought-like (CoT-like) guidance learning, termed Chain-of-Perform (CoP). First, we employ a transformer-based network architecture designed to achieve CoP guidance, enabling the generation of both general and professional audio. Second, we implement a multi-stage training framework that follows step-by-step guidance to ensure the generation of high-quality sound effects. Third, we develop a CoP multi-modal dataset, guided by video, to support step-by-step sound effects generation. Evaluation results highlight the advantages of the proposed multi-stage CoP generative framework compared to the state-of-the-art models on a variety of datasets, with FAD 0.79 to 0.74 (+6.33%), CLIP 16.12 to 17.70 (+9.80%) on VGGSound, SI-SDR 1.98dB to 3.35dB (+69.19%), MOS 2.94 to 3.49(+18.71%) on PianoYT-2h, and SI-SDR 2.22dB to 3.21dB (+44.59%), MOS 3.07 to 3.42 (+11.40%) on Piano-10h.
Abstract:Traffic Atomic Activity which describes traffic patterns for topological intersection dynamics is a crucial topic for the advancement of intelligent driving systems. However, existing atomic activity datasets are collected from an egocentric view, which cannot support the scenarios where traffic activities in an entire intersection are required. Moreover, existing datasets only provide video-level atomic activity annotations, which require exhausting efforts to manually trim the videos for recognition and limit their applications to untrimmed videos. To bridge this gap, we introduce the Aerial Traffic Atomic Activity Recognition and Segmentation (ATARS) dataset, the first aerial dataset designed for multi-label atomic activity analysis. We offer atomic activity labels for each frame, which accurately record the intervals for traffic activities. Moreover, we propose a novel task, Multi-label Temporal Atomic Activity Recognition, enabling the study of accurate temporal localization for atomic activity and easing the burden of manual video trimming for recognition. We conduct extensive experiments to evaluate existing state-of-the-art models on both atomic activity recognition and temporal atomic activity segmentation. The results highlight the unique challenges of our ATARS dataset, such as recognizing extremely small objects' activities. We further provide comprehensive discussion analyzing these challenges and offer valuable insights for future direction to improve recognizing atomic activity in aerial view. Our source code and dataset are available at https://github.com/magecliff96/ATARS/
Abstract:Several backbone models pre-trained on general domain datasets can encode a sentence into a widely useful embedding. Such sentence embeddings can be further enhanced by domain adaptation that adapts a backbone model to a specific domain. However, domain adaptation for low-resource languages like Japanese is often difficult due to the scarcity of large-scale labeled datasets. To overcome this, this paper introduces SDJC (Self-supervised Domain adaptation for Japanese sentence embeddings with Contrastive learning) that utilizes a data generator to generate sentences, which have the same syntactic structure to a sentence in an unlabeled specific domain corpus but convey different semantic meanings. Generated sentences are then used to boost contrastive learning that adapts a backbone model to accurately discriminate sentences in the specific domain. In addition, the components of SDJC like a backbone model and a method to adapt it need to be carefully selected, but no benchmark dataset is available for Japanese. Thus, a comprehensive Japanese STS (Semantic Textual Similarity) benchmark dataset is constructed by combining datasets machine-translated from English with existing datasets. The experimental results validates the effectiveness of SDJC on two domain-specific downstream tasks as well as the usefulness of the constructed dataset. Datasets, codes and backbone models adapted by SDJC are available on our github repository https://github.com/ccilab-doshisha/SDJC.
Abstract:Despite the success of contrastive learning (CL) in vision and language, its theoretical foundations and mechanisms for building representations remain poorly understood. In this work, we build connections between noise contrastive estimation losses widely used in CL and distribution alignment with entropic optimal transport (OT). This connection allows us to develop a family of different losses and multistep iterative variants for existing CL methods. Intuitively, by using more information from the distribution of latents, our approach allows a more distribution-aware manipulation of the relationships within augmented sample sets. We provide theoretical insights and experimental evidence demonstrating the benefits of our approach for {\em generalized contrastive alignment}. Through this framework, it is possible to leverage tools in OT to build unbalanced losses to handle noisy views and customize the representation space by changing the constraints on alignment. By reframing contrastive learning as an alignment problem and leveraging existing optimization tools for OT, our work provides new insights and connections between different self-supervised learning models in addition to new tools that can be more easily adapted to incorporate domain knowledge into learning.
Abstract:Music composition has long been recognized as a significant art form. However, existing digital audio workstations and music production software often present high entry barriers for users lacking formal musical training. To address this, we introduce ComposeOn, a music theory-based tool designed for users with limited musical knowledge. ComposeOn enables users to easily extend their melodic ideas into complete compositions and offers simple editing features. By integrating music theory, it explains music creation at beginner, intermediate, and advanced levels. Our user study (N=10) compared ComposeOn with the baseline method, Suno AI, demonstrating that ComposeOn provides a more accessible and enjoyable composing and learning experience for individuals with limited musical skills. ComposeOn bridges the gap between theory and practice, offering an innovative solution as both a composition aid and music education platform. The study also explores the differences between theory-based music creation and generative music, highlighting the former's advantages in personal expression and learning.
Abstract:One fascinating aspect of pre-trained Audio-Language Models (ALMs) learning is their impressive zero-shot generalization capability and test-time adaptation (TTA) methods aiming to improve domain performance without annotations. However, previous test time adaptation (TTA) methods for ALMs in zero-shot classification tend to be stuck in incorrect model predictions. In order to further boost the performance, we propose multiple guidance on prompt learning without annotated labels. First, guidance of consistency on both context tokens and domain tokens of ALMs is set. Second, guidance of both consistency across multiple augmented views of each single test sample and contrastive learning across different test samples is set. Third, we propose a corresponding end-end learning framework for the proposed test-time adaptation method without annotated labels. We extensively evaluate our approach on 12 downstream tasks across domains, our proposed adaptation method leads to 4.41% (max 7.50%) average zero-shot performance improvement in comparison with the state-of-the-art models.
Abstract:Generating sound effects for product-level videos, where only a small amount of labeled data is available for diverse scenes, requires the production of high-quality sounds in few-shot settings. To tackle the challenge of limited labeled data in real-world scenes, we introduce YingSound, a foundation model designed for video-guided sound generation that supports high-quality audio generation in few-shot settings. Specifically, YingSound consists of two major modules. The first module uses a conditional flow matching transformer to achieve effective semantic alignment in sound generation across audio and visual modalities. This module aims to build a learnable audio-visual aggregator (AVA) that integrates high-resolution visual features with corresponding audio features at multiple stages. The second module is developed with a proposed multi-modal visual-audio chain-of-thought (CoT) approach to generate finer sound effects in few-shot settings. Finally, an industry-standard video-to-audio (V2A) dataset that encompasses various real-world scenarios is presented. We show that YingSound effectively generates high-quality synchronized sounds across diverse conditional inputs through automated evaluations and human studies. Project Page: \url{https://giantailab.github.io/yingsound/}