DRCap: Decoding CLAP Latents with Retrieval-augmented Generation for Zero-shot Audio Captioning

While automated audio captioning (AAC) has made notable progress, traditional fully supervised AAC models still face two critical challenges: the need for expensive audio-text pair data for training and performance degradation when transferring across domains. To overcome these limitations, we present DRCap, a data-efficient and flexible zero-shot audio captioning system that requires text-only data for training and can quickly adapt to new domains without additional fine-tuning. DRCap integrates a contrastive language-audio pre-training (CLAP) model and a large-language model (LLM) as its backbone. During training, the model predicts the ground-truth caption with a fixed text encoder from CLAP, whereas, during inference, the text encoder is replaced with the audio encoder to generate captions for audio clips in a zero-shot manner. To mitigate the modality gap of the CLAP model, we use both the projection strategy from the encoder side and the retrieval-augmented generation strategy from the decoder side. Specifically, audio embeddings are first projected onto a text embedding support to absorb extensive semantic information within the joint multi-modal space of CLAP. At the same time, similar captions retrieved from a datastore are fed as prompts to instruct the LLM, incorporating external knowledge to take full advantage of its strong generative capability. Conditioned on both the projected CLAP embedding and the retrieved similar captions, the model is able to produce a more accurate and semantically rich textual description. By tailoring the text embedding support and the caption datastore to the target domain, DRCap acquires a robust ability to adapt to new domains in a training-free manner. Experimental results demonstrate that DRCap outperforms all other zero-shot models in in-domain scenarios and achieves state-of-the-art performance in cross-domain scenarios.

Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancement

Diffusion-based generative models have recently achieved remarkable results in speech and vocal enhancement due to their ability to model complex speech data distributions. While these models generalize well to unseen acoustic environments, they may not achieve the same level of fidelity as the discriminative models specifically trained to enhance particular acoustic conditions. In this paper, we propose Ex-Diff, a novel score-based diffusion model that integrates the latent representations produced by a discriminative model to improve speech and vocal enhancement, which combines the strengths of both generative and discriminative models. Experimental results on the widely used MUSDB dataset show relative improvements of 3.7% in SI-SDR and 10.0% in SI-SIR compared to the baseline diffusion model for speech and vocal enhancement tasks, respectively. Additionally, case studies are provided to further illustrate and analyze the complementary nature of generative and discriminative models in this context.

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a language-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the multi-modal representation alignment nature of the contrastive language-audio pre-trained model (CLAP). In a vanilla language-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding for the TSE model, while during inference, user language queries are encoded by CLAP text encoder. This straightforward approach faces challenges due to the modality gap between training and inference queries and information leakage from direct exposure to target audio during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and inference and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability.

SymPAC: Scalable Symbolic Music Generation With Prompts And Constraints

Progress in the task of symbolic music generation may be lagging behind other tasks like audio and text generation, in part because of the scarcity of symbolic training data. In this paper, we leverage the greater scale of audio music data by applying pre-trained MIR models (for transcription, beat tracking, structure analysis, etc.) to extract symbolic events and encode them into token sequences. To the best of our knowledge, this work is the first to demonstrate the feasibility of training symbolic generation models solely from auto-transcribed audio data. Furthermore, to enhance the controllability of the trained model, we introduce SymPAC (Symbolic Music Language Model with Prompting And Constrained Generation), which is distinguished by using (a) prompt bars in encoding and (b) a technique called Constrained Generation via Finite State Machines (FSMs) during inference time. We show the flexibility and controllability of this approach, which may be critical in making music AI useful to creators and users.

Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

Recent advancements in audio generation have been significantly propelled by the capabilities of Large Language Models (LLMs). The existing research on audio LLM has primarily focused on enhancing the architecture and scale of audio language models, as well as leveraging larger datasets, and generally, acoustic codecs, such as EnCodec, are used for audio tokenization. However, these codecs were originally designed for audio compression, which may lead to suboptimal performance in the context of audio LLM. Our research aims to address the shortcomings of current audio LLM codecs, particularly their challenges in maintaining semantic integrity in generated audio. For instance, existing methods like VALL-E, which condition acoustic token generation on text transcriptions, often suffer from content inaccuracies and elevated word error rates (WER) due to semantic misinterpretations of acoustic tokens, resulting in word skipping and errors. To overcome these issues, we propose a straightforward yet effective approach called X-Codec. X-Codec incorporates semantic features from a pre-trained semantic encoder before the Residual Vector Quantization (RVQ) stage and introduces a semantic reconstruction loss after RVQ. By enhancing the semantic ability of the codec, X-Codec significantly reduces WER in speech synthesis tasks and extends these benefits to non-speech applications, including music and sound generation. Our experiments in text-to-speech, music continuation, and text-to-sound tasks demonstrate that integrating semantic information substantially improves the overall performance of language models in audio generation. Our code and demo are available (Demo: https://x-codec-audio.github.io Code: https://github.com/zhenye234/xcodec)

Foundation Models for Music: A Survey

In recent years, foundation models (FMs) such as large language models (LLMs) and latent diffusion models (LDMs) have profoundly impacted diverse sectors, including music. This comprehensive review examines state-of-the-art (SOTA) pre-trained models and foundation models in music, spanning from representation learning, generative learning and multimodal learning. We first contextualise the significance of music in various industries and trace the evolution of AI in music. By delineating the modalities targeted by foundation models, we discover many of the music representations are underexplored in FM development. Then, emphasis is placed on the lack of versatility of previous methods on diverse music applications, along with the potential of FMs in music understanding, generation and medical application. By comprehensively exploring the details of the model pre-training paradigm, architectural choices, tokenisation, finetuning methodologies and controllability, we emphasise the important topics that should have been well explored, like instruction tuning and in-context learning, scaling law and emergent ability, as well as long-sequence modelling etc. A dedicated section presents insights into music agents, accompanied by a thorough analysis of datasets and evaluations essential for pre-training and downstream tasks. Finally, by underscoring the vital importance of ethical considerations, we advocate that following research on FM for music should focus more on such issues as interpretability, transparency, human responsibility, and copyright issues. The paper offers insights into future challenges and trends on FMs for music, aiming to shape the trajectory of human-AI collaboration in the music realm.

Universal Sound Separation with Self-Supervised Audio Masked Autoencoder

Universal sound separation (USS) is a task of separating mixtures of arbitrary sound sources. Typically, universal separation models are trained from scratch in a supervised manner, using labeled data. Self-supervised learning (SSL) is an emerging deep learning approach that leverages unlabeled data to obtain task-agnostic representations, which can benefit many downstream tasks. In this paper, we propose integrating a self-supervised pre-trained model, namely the audio masked autoencoder (A-MAE), into a universal sound separation system to enhance its separation performance. We employ two strategies to utilize SSL embeddings: freezing or updating the parameters of A-MAE during fine-tuning. The SSL embeddings are concatenated with the short-time Fourier transform (STFT) to serve as input features for the separation model. We evaluate our methods on the AudioSet dataset, and the experimental results indicate that the proposed methods successfully enhance the separation performance of a state-of-the-art ResUNet-based USS model.

MusicScore: A Dataset for Music Score Modeling and Generation

Music scores are written representations of music and contain rich information about musical components. The visual information on music scores includes notes, rests, staff lines, clefs, dynamics, and articulations. This visual information in music scores contains more semantic information than audio and symbolic representations of music. Previous music score datasets have limited sizes and are mainly designed for optical music recognition (OMR). There is a lack of research on creating a large-scale benchmark dataset for music modeling and generation. In this work, we propose MusicScore, a large-scale music score dataset collected and processed from the International Music Score Library Project (IMSLP). MusicScore consists of image-text pairs, where the image is a page of a music score and the text is the metadata of the music. The metadata of MusicScore is extracted from the general information section of the IMSLP pages. The metadata includes rich information about the composer, instrument, piece style, and genre of the music pieces. MusicScore is curated into small, medium, and large scales of 400, 14k, and 200k image-text pairs with varying diversity, respectively. We build a score generation system based on a UNet diffusion model to generate visually readable music scores conditioned on text descriptions to benchmark the MusicScore dataset for music score generation. MusicScore is released to the public at https://huggingface.co/datasets/ZheqiDAI/MusicScore.

Towards Out-of-Distribution Detection in Vocoder Recognition via Latent Feature Reconstruction

Advancements in synthesized speech have created a growing threat of impersonation, making it crucial to develop deepfake algorithm recognition. One significant aspect is out-of-distribution (OOD) detection, which has gained notable attention due to its important role in deepfake algorithm recognition. However, most of the current approaches for detecting OOD in deepfake algorithm recognition rely on probability-score or classified-distance, which may lead to limitations in the accuracy of the sample at the edge of the threshold. In this study, we propose a reconstruction-based detection approach that employs an autoencoder architecture to compress and reconstruct the acoustic feature extracted from a pre-trained WavLM model. Each acoustic feature belonging to a specific vocoder class is only aptly reconstructed by its corresponding decoder. When none of the decoders can satisfactorily reconstruct a feature, it is classified as an OOD sample. To enhance the distinctiveness of the reconstructed features by each decoder, we incorporate contrastive learning and an auxiliary classifier to further constrain the reconstructed feature. Experiments demonstrate that our proposed approach surpasses baseline systems by a relative margin of 10\% in the evaluation dataset. Ablation studies further validate the effectiveness of both the contrastive constraint and the auxiliary classifier within our proposed approach.

WavCraft: Audio Editing and Generation with Natural Language Prompts

We introduce WavCraft, a collective system that leverages large language models (LLMs) to connect diverse task-specific models for audio content creation and editing. Specifically, WavCraft describes the content of raw sound materials in natural language and prompts the LLM conditioned on audio descriptions and users' requests. WavCraft leverages the in-context learning ability of the LLM to decomposes users' instructions into several tasks and tackle each task collaboratively with audio expert modules. Through task decomposition along with a set of task-specific models, WavCraft follows the input instruction to create or edit audio content with more details and rationales, facilitating users' control. In addition, WavCraft is able to cooperate with users via dialogue interaction and even produce the audio content without explicit user commands. Experiments demonstrate that WavCraft yields a better performance than existing methods, especially when adjusting the local regions of audio clips. Moreover, WavCraft can follow complex instructions to edit and even create audio content on the top of input recordings, facilitating audio producers in a broader range of applications. Our implementation and demos are available at https://github.com/JinhuaLiang/WavCraft.