Abstract:Locating the right sound effect efficiently is an important yet challenging topic for audio production. Most current sound-searching systems rely on pre-annotated audio labels created by humans, which can be time-consuming to produce and prone to inaccuracies, limiting the efficiency of audio production. Following the recent advancement of contrastive language-audio pre-training (CLAP) models, we explore an alternative CLAP-based sound-searching system (CLAP-UI) that does not rely on human annotations. To evaluate the effectiveness of CLAP-UI, we conducted comparative experiments with a widely used sound effect searching platform, the BBC Sound Effect Library. Our study evaluates user performance, cognitive load, and satisfaction through ecologically valid tasks based on professional sound-searching workflows. Our result shows that CLAP-UI demonstrated significantly enhanced productivity and reduced frustration while maintaining comparable cognitive demands. We also qualitatively analyzed the participants' feedback, which offered valuable perspectives on the design of future AI-assisted sound search systems.
Abstract:Fish Feeding Intensity Assessment (FFIA) is crucial in industrial aquaculture management. Recent multi-modal approaches have shown promise in improving FFIA robustness and efficiency. However, these methods face significant challenges when adapting to new fish species or environments due to catastrophic forgetting and the lack of suitable datasets. To address these limitations, we first introduce AV-CIL-FFIA, a new dataset comprising 81,932 labelled audio-visual clips capturing feeding intensities across six different fish species in real aquaculture environments. Then, we pioneer audio-visual class incremental learning (CIL) for FFIA and demonstrate through benchmarking on AV-CIL-FFIA that it significantly outperforms single-modality methods. Existing CIL methods rely heavily on historical data. Exemplar-based approaches store raw samples, creating storage challenges, while exemplar-free methods avoid data storage but struggle to distinguish subtle feeding intensity variations across different fish species. To overcome these limitations, we introduce HAIL-FFIA, a novel audio-visual class-incremental learning framework that bridges this gap with a prototype-based approach that achieves exemplar-free efficiency while preserving essential knowledge through compact feature representations. Specifically, HAIL-FFIA employs hierarchical representation learning with a dual-path knowledge preservation mechanism that separates general intensity knowledge from fish-specific characteristics. Additionally, it features a dynamic modality balancing system that adaptively adjusts the importance of audio versus visual information based on feeding behaviour stages. Experimental results show that HAIL-FFIA is superior to SOTA methods on AV-CIL-FFIA, achieving higher accuracy with lower storage needs while effectively mitigating catastrophic forgetting in incremental fish species learning.
Abstract:Existing 3D Gaussian Splatting (3DGS) methods for hand rendering rely on rigid skeletal motion with an oversimplified non-rigid motion model, which fails to capture fine geometric and appearance details. Additionally, they perform densification based solely on per-point gradients and process poses independently, ignoring spatial and temporal correlations. These limitations lead to geometric detail loss, temporal instability, and inefficient point distribution. To address these issues, we propose HandSplat, a novel Gaussian Splatting-based framework that enhances both fidelity and stability for hand rendering. To improve fidelity, we extend standard 3DGS attributes with implicit geometry and appearance embeddings for finer non-rigid motion modeling while preserving the static hand characteristic modeled by original 3DGS attributes. Additionally, we introduce a local gradient-aware densification strategy that dynamically refines Gaussian density in high-variation regions. To improve stability, we incorporate pose-conditioned attribute regularization to encourage attribute consistency across similar poses, mitigating temporal artifacts. Extensive experiments on InterHand2.6M demonstrate that HandSplat surpasses existing methods in fidelity and stability while achieving real-time performance. We will release the code and pre-trained models upon acceptance.
Abstract:We tackle the task of long-form music generation--particularly the challenging \textbf{lyrics-to-song} problem--by introducing YuE, a family of open foundation models based on the LLaMA2 architecture. Specifically, YuE scales to trillions of tokens and generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment. It achieves this through (1) track-decoupled next-token prediction to overcome dense mixture signals, (2) structural progressive conditioning for long-context lyrical alignment, and (3) a multitask, multiphase pre-training recipe to converge and generalize. In addition, we redesign the in-context learning technique for music generation, enabling versatile style transfer (e.g., converting Japanese city pop into an English rap while preserving the original accompaniment) and bidirectional generation. Through extensive evaluation, we demonstrate that YuE matches or even surpasses some of the proprietary systems in musicality and vocal agility. In addition, fine-tuning YuE enables additional controls and enhanced support for tail languages. Furthermore, beyond generation, we show that YuE's learned representations can perform well on music understanding tasks, where the results of YuE match or exceed state-of-the-art methods on the MARBLE benchmark. Keywords: lyrics2song, song generation, long-form, foundation model, music generation
Abstract:Recent advancements in audio tokenization have significantly enhanced the integration of audio capabilities into large language models (LLMs). However, audio understanding and generation are often treated as distinct tasks, hindering the development of truly unified audio-language models. While instruction tuning has demonstrated remarkable success in improving generalization and zero-shot learning across text and vision, its application to audio remains largely unexplored. A major obstacle is the lack of comprehensive datasets that unify audio understanding and generation. To address this, we introduce Audio-FLAN, a large-scale instruction-tuning dataset covering 80 diverse tasks across speech, music, and sound domains, with over 100 million instances. Audio-FLAN lays the foundation for unified audio-language models that can seamlessly handle both understanding (e.g., transcription, comprehension) and generation (e.g., speech, music, sound) tasks across a wide range of audio domains in a zero-shot manner. The Audio-FLAN dataset is available on HuggingFace and GitHub and will be continuously updated.
Abstract:Recent advances in text-based large language models (LLMs), particularly in the GPT series and the o1 model, have demonstrated the effectiveness of scaling both training-time and inference-time compute. However, current state-of-the-art TTS systems leveraging LLMs are often multi-stage, requiring separate models (e.g., diffusion models after LLM), complicating the decision of whether to scale a particular model during training or testing. This work makes the following contributions: First, we explore the scaling of train-time and inference-time compute for speech synthesis. Second, we propose a simple framework Llasa for speech synthesis that employs a single-layer vector quantizer (VQ) codec and a single Transformer architecture to fully align with standard LLMs such as Llama. Our experiments reveal that scaling train-time compute for Llasa consistently improves the naturalness of synthesized speech and enables the generation of more complex and accurate prosody patterns. Furthermore, from the perspective of scaling inference-time compute, we employ speech understanding models as verifiers during the search, finding that scaling inference-time compute shifts the sampling modes toward the preferences of specific verifiers, thereby improving emotional expressiveness, timbre consistency, and content accuracy. In addition, we released the checkpoint and training code for our TTS model (1B, 3B, 8B) and codec model publicly available.
Abstract:With the emergence of audio-language models, constructing large-scale paired audio-language datasets has become essential yet challenging for model development, primarily due to the time-intensive and labour-heavy demands involved. While large language models (LLMs) have improved the efficiency of synthetic audio caption generation, current approaches struggle to effectively extract and incorporate detailed audio information. In this paper, we propose an automated pipeline that integrates audio-language models for fine-grained content extraction, LLMs for synthetic caption generation, and a contrastive language-audio pretraining (CLAP) model-based refinement process to improve the quality of captions. Specifically, we employ prompt chaining techniques in the content extraction stage to obtain accurate and fine-grained audio information, while we use the refinement process to mitigate potential hallucinations in the generated captions. Leveraging the AudioSet dataset and the proposed approach, we create AudioSetCaps, a dataset comprising 1.9 million audio-caption pairs, the largest audio-caption dataset at the time of writing. The models trained with AudioSetCaps achieve state-of-the-art performance on audio-text retrieval with R@1 scores of 46.3% for text-to-audio and 59.7% for audio-to-text retrieval and automated audio captioning with the CIDEr score of 84.8. As our approach has shown promising results with AudioSetCaps, we create another dataset containing 4.1 million synthetic audio-language pairs based on the Youtube-8M and VGGSound datasets. To facilitate research in audio-language learning, we have made our pipeline, datasets with 6 million audio-language pairs, and pre-trained models publicly available at https://github.com/JishengBai/AudioSetCaps.
Abstract:Language-queried audio source separation (LASS) focuses on separating sounds using textual descriptions of the desired sources. Current methods mainly use discriminative approaches, such as time-frequency masking, to separate target sounds and minimize interference from other sources. However, these models face challenges when separating overlapping soundtracks, which may lead to artifacts such as spectral holes or incomplete separation. Rectified flow matching (RFM), a generative model that establishes linear relations between the distribution of data and noise, offers superior theoretical properties and simplicity, but has not yet been explored in sound separation. In this work, we introduce FlowSep, a new generative model based on RFM for LASS tasks. FlowSep learns linear flow trajectories from noise to target source features within the variational autoencoder (VAE) latent space. During inference, the RFM-generated latent features are reconstructed into a mel-spectrogram via the pre-trained VAE decoder, followed by a pre-trained vocoder to synthesize the waveform. Trained on 1,680 hours of audio data, FlowSep outperforms the state-of-the-art models across multiple benchmarks, as evaluated with subjective and objective metrics. Additionally, our results show that FlowSep surpasses a diffusion-based LASS model in both separation quality and inference efficiency, highlighting its strong potential for audio source separation tasks. Code, pre-trained models and demos can be found at: https://audio-agi.github.io/FlowSep_demo/.
Abstract:Significant improvement has been achieved in automated audio captioning (AAC) with recent models. However, these models have become increasingly large as their performance is enhanced. In this work, we propose a knowledge distillation (KD) framework for AAC. Our analysis shows that in the encoder-decoder based AAC models, it is more effective to distill knowledge into the encoder as compared with the decoder. To this end, we incorporate encoder-level KD loss into training, in addition to the standard supervised loss and sequence-level KD loss. We investigate two encoder-level KD methods, based on mean squared error (MSE) loss and contrastive loss, respectively. Experimental results demonstrate that contrastive KD is more robust than MSE KD, exhibiting superior performance in data-scarce situations. By leveraging audio-only data into training in the KD framework, our student model achieves competitive performance, with an inference speed that is 19 times faster\footnote{An online demo is available at \url{https://huggingface.co/spaces/wsntxxn/efficient_audio_captioning}}.
Abstract:Sound event localization and detection (SELD) aims to determine the appearance of sound classes, together with their Direction of Arrival (DOA). However, current SELD systems can only predict the activities of specific classes, for example, 13 classes in DCASE challenges. In this paper, we propose text-queried target sound event localization (SEL), a new paradigm that allows the user to input the text to describe the sound event, and the SEL model can predict the location of the related sound event. The proposed task presents a more user-friendly way for human-computer interaction. We provide a benchmark study for the proposed task and perform experiments on datasets created by simulated room impulse response (RIR) and real RIR to validate the effectiveness of the proposed methods. We hope that our benchmark will inspire the interest and additional research for text-queried sound source localization.