We propose the first unsupervised and learning-based method to identify interpretable directions in the h-space of pre-trained diffusion models. Our method is derived from an existing technique that operates on the GAN latent space. In a nutshell, we employ a shift control module for pre-trained diffusion models to manipulate a sample into a shifted version of itself, followed by a reconstructor to reproduce both the type and the strength of the manipulation. By jointly optimizing them, the model will spontaneously discover disentangled and interpretable directions. To prevent the discovery of meaningless and destructive directions, we employ a discriminator to maintain the fidelity of shifted sample. Due to the iterative generative process of diffusion models, our training requires a substantial amount of GPU VRAM to store numerous intermediate tensors for back-propagating gradient. To address this issue, we first propose a general VRAM-efficient training algorithm based on gradient checkpointing technique to back-propagate any gradient through the whole generative process, with acceptable occupancy of VRAM and sacrifice of training efficiency. Compared with existing related works on diffusion models, our method inherently identifies global and scalable directions, without necessitating any other complicated procedures. Extensive experiments on various datasets demonstrate the effectiveness of our method.
Multi-modal contrastive representation (MCR) of more than three modalities is critical in multi-modal learning. Although recent methods showcase impressive achievements, the high dependence on large-scale, high-quality paired data and the expensive training costs limit their further development. Inspired by recent C-MCR, this paper proposes Extending Multimodal Contrastive Representation (Ex-MCR), a training-efficient and paired-data-free method to flexibly learn unified contrastive representation space for more than three modalities by integrating the knowledge of existing MCR spaces. Specifically, Ex-MCR aligns multiple existing MCRs into the same based MCR, which can effectively preserve the original semantic alignment of the based MCR. Besides, we comprehensively enhance the entire learning pipeline for aligning MCR spaces from the perspectives of training data, architecture, and learning objectives. With the preserved original modality alignment and the enhanced space alignment, Ex-MCR shows superior representation learning performance and excellent modality extensibility. To demonstrate the effectiveness of Ex-MCR, we align the MCR spaces of CLAP (audio-text) and ULIP (3D-vision) into the CLIP (vision-text), leveraging the overlapping text and image modality, respectively. Remarkably, without using any paired data, Ex-MCR learns a 3D-image-text-audio unified contrastive representation, and it achieves state-of-the-art performance on audio-visual, 3D-image, audio-text, visual-text retrieval, and 3D object classification tasks. More importantly, extensive qualitative results further demonstrate the emergent semantic alignment between the extended modalities (e.g., audio and 3D), which highlights the great potential of modality extensibility.
Large Language models (LLM) have demonstrated the capability to handle a variety of generative tasks. This paper presents the UniAudio system, which, unlike prior task-specific approaches, leverages LLM techniques to generate multiple types of audio (including speech, sounds, music, and singing) with given input conditions. UniAudio 1) first tokenizes all types of target audio along with other condition modalities, 2) concatenates source-target pair as a single sequence, and 3) performs next-token prediction using LLM. Also, a multi-scale Transformer model is proposed to handle the overly long sequences caused by the residual vector quantization based neural codec in tokenization. Training of UniAudio is scaled up to 165K hours of audio and 1B parameters, based on all generative tasks, aiming to obtain sufficient prior knowledge not only in the intrinsic properties of audio but also the inter-relationship between audio and other modalities. Therefore, the trained UniAudio model has the potential to become a foundation model for universal audio generation: it shows strong capability in all trained tasks and can seamlessly support new audio generation tasks after simple fine-tuning. Experiments demonstrate that UniAudio achieves state-of-the-art or at least competitive results on most of the 11 tasks. Demo and code are released at https://github.com/yangdongchao/UniAudio
Direct speech-to-speech translation (S2ST) with discrete self-supervised representations has achieved remarkable accuracy, but is unable to preserve the speaker timbre of the source speech during translation. Meanwhile, the scarcity of high-quality speaker-parallel data poses a challenge for learning style transfer between source and target speech. We propose an S2ST framework with an acoustic language model based on discrete units from a self-supervised model and a neural codec for style transfer. The acoustic language model leverages self-supervised in-context learning, acquiring the ability for style transfer without relying on any speaker-parallel data, thereby overcoming the issue of data scarcity. By using extensive training data, our model achieves zero-shot cross-lingual style transfer on previously unseen source languages. Experiments show that our model generates translated speeches with high fidelity and style similarity. Audio samples are available at http://stylelm.github.io/ .
Recently, there has been a growing interest in the field of controllable Text-to-Speech (TTS). While previous studies have relied on users providing specific style factor values based on acoustic knowledge or selecting reference speeches that meet certain requirements, generating speech solely from natural text prompts has emerged as a new challenge for researchers. This challenge arises due to the scarcity of high-quality speech datasets with natural text style prompt and the absence of advanced text-controllable TTS models. In light of this, 1) we propose TextrolSpeech, which is the first large-scale speech emotion dataset annotated with rich text attributes. The dataset comprises 236,220 pairs of style prompt in natural text descriptions with five style factors and corresponding speech samples. Through iterative experimentation, we introduce a multi-stage prompt programming approach that effectively utilizes the GPT model for generating natural style descriptions in large volumes. 2) Furthermore, to address the need for generating audio with greater style diversity, we propose an efficient architecture called Salle. This architecture treats text controllable TTS as a language model task, utilizing audio codec codes as an intermediate representation to replace the conventional mel-spectrogram. Finally, we successfully demonstrate the ability of the proposed model by showing a comparable performance in the controllable TTS task. Audio samples are available at https://sall-e.github.io/
3D scene understanding has gained significant attention due to its wide range of applications. However, existing methods for 3D scene understanding are limited to specific downstream tasks, which hinders their practicality in real-world applications. This paper presents Chat-3D, which combines the 3D visual perceptual ability of pre-trained 3D representations and the impressive reasoning and conversation capabilities of advanced LLMs to achieve the first universal dialogue systems for 3D scenes. Specifically, we align 3D representations into the feature space of LLMs, thus enabling LLMs to perceive the 3D world. Given the scarcity of 3D scene-text data, we propose a three-stage training strategy to efficiently utilize the available data for better alignment. To enhance the reasoning ability and develop a user-friendly interaction scheme, we further construct a high-quality object-centric 3D instruction dataset and design an associated object-centric prompt. Our experiments show that Chat-3D achieves an impressive ability to comprehend diverse instructions for 3D scenes, engage in intricate spatial reasoning, and incorporate external knowledge into its responses. Chat-3D achieves a 75.6% relative score compared with GPT-4 on the constructed instruction dataset.
3D visual grounding aims to localize the target object in a 3D point cloud by a free-form language description. Typically, the sentences describing the target object tend to provide information about its relative relation between other objects and its position within the whole scene. In this work, we propose a relation-aware one-stage framework, named 3D Relative Position-aware Network (3DRP-Net), which can effectively capture the relative spatial relationships between objects and enhance object attributes. Specifically, 1) we propose a 3D Relative Position Multi-head Attention (3DRP-MA) module to analyze relative relations from different directions in the context of object pairs, which helps the model to focus on the specific object relations mentioned in the sentence. 2) We designed a soft-labeling strategy to alleviate the spatial ambiguity caused by redundant points, which further stabilizes and enhances the learning process through a constant and discriminative distribution. Extensive experiments conducted on three benchmarks (i.e., ScanRefer and Nr3D/Sr3D) demonstrate that our method outperforms all the state-of-the-art methods in general. The source code will be released on GitHub.
In the field of music information retrieval (MIR), cover song identification (CSI) is a challenging task that aims to identify cover versions of a query song from a massive collection. Existing works still suffer from high intra-song variances and inter-song correlations, due to the entangled nature of version-specific and version-invariant factors in their modeling. In this work, we set the goal of disentangling version-specific and version-invariant factors, which could make it easier for the model to learn invariant music representations for unseen query songs. We analyze the CSI task in a disentanglement view with the causal graph technique, and identify the intra-version and inter-version effects biasing the invariant learning. To block these effects, we propose the disentangled music representation learning framework (DisCover) for CSI. DisCover consists of two critical components: (1) Knowledge-guided Disentanglement Module (KDM) and (2) Gradient-based Adversarial Disentanglement Module (GADM), which block intra-version and inter-version biased effects, respectively. KDM minimizes the mutual information between the learned representations and version-variant factors that are identified with prior domain knowledge. GADM identifies version-variant factors by simulating the representation transitions between intra-song versions, and exploits adversarial distillation for effect blocking. Extensive comparisons with best-performing methods and in-depth analysis demonstrate the effectiveness of DisCover and the and necessity of disentanglement for CSI.
3D visual grounding involves finding a target object in a 3D scene that corresponds to a given sentence query. Although many approaches have been proposed and achieved impressive performance, they all require dense object-sentence pair annotations in 3D point clouds, which are both time-consuming and expensive. To address the problem that fine-grained annotated data is difficult to obtain, we propose to leverage weakly supervised annotations to learn the 3D visual grounding model, i.e., only coarse scene-sentence correspondences are used to learn object-sentence links. To accomplish this, we design a novel semantic matching model that analyzes the semantic similarity between object proposals and sentences in a coarse-to-fine manner. Specifically, we first extract object proposals and coarsely select the top-K candidates based on feature and class similarity matrices. Next, we reconstruct the masked keywords of the sentence using each candidate one by one, and the reconstructed accuracy finely reflects the semantic similarity of each candidate to the query. Additionally, we distill the coarse-to-fine semantic matching knowledge into a typical two-stage 3D visual grounding model, which reduces inference costs and improves performance by taking full advantage of the well-studied structure of the existing architectures. We conduct extensive experiments on ScanRefer, Nr3D, and Sr3D, which demonstrate the effectiveness of our proposed method.
Most sign language translation (SLT) methods to date require the use of gloss annotations to provide additional supervision information, however, the acquisition of gloss is not easy. To solve this problem, we first perform an analysis of existing models to confirm how gloss annotations make SLT easier. We find that it can provide two aspects of information for the model, 1) it can help the model implicitly learn the location of semantic boundaries in continuous sign language videos, 2) it can help the model understand the sign language video globally. We then propose \emph{gloss attention}, which enables the model to keep its attention within video segments that have the same semantics locally, just as gloss helps existing models do. Furthermore, we transfer the knowledge of sentence-to-sentence similarity from the natural language model to our gloss attention SLT network (GASLT) to help it understand sign language videos at the sentence level. Experimental results on multiple large-scale sign language datasets show that our proposed GASLT model significantly outperforms existing methods. Our code is provided in \url{https://github.com/YinAoXiong/GASLT}.