Yi Yuan

Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA). LASS aims to separate a target sound from an audio mixture given a natural language query, which provides a natural and scalable interface for digital audio applications. Recent works on LASS, despite attaining promising separation performance on specific sources (e.g., musical instruments, limited classes of audio events), are unable to separate audio concepts in the open domain. In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries. We train AudioSep on large-scale multimodal datasets and extensively evaluate its capabilities on numerous tasks including audio event separation, musical instrument separation, and speech enhancement. AudioSep demonstrates strong separation performance and impressive zero-shot generalization ability using audio captions or text labels as queries, substantially outperforming previous audio-queried and language-queried sound separation models. Specifically, AudioSep achieved strong results including a Signal-to-Distortion Ratio Improvement (SDRi) of 7.74 dB across 527 sound classes of the AudioSet; 9.14 dB on the VGGSound dataset; 8.22 dB on the AudioCaps dataset; 6.85 dB on the Clotho dataset; 10.51 dB on the MUSIC dataset; 10.04 dB on the ESC-50 dataset; 8.16 dB on the DCASE 2024 Task 9 dataset; and an SSNR of 9.21 dB on the VoicebankDemand dataset.

Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from the simplicity and scarcity of the training data. This work aims to create a large-scale audio dataset with rich captions for improving audio generation models. We first develop an automated pipeline to generate detailed captions by transforming predicted visual captions, audio captions, and tagging labels into comprehensive descriptions using a Large Language Model (LLM). The resulting dataset, Sound-VECaps, comprises 1.66M high-quality audio-caption pairs with enriched details including audio event orders, occurred places and environment information. We then demonstrate that training the text-to-audio generation models with Sound-VECaps significantly improves the performance on complex prompts. Furthermore, we conduct ablation studies of the models on several downstream audio-language tasks, showing the potential of Sound-VECaps in advancing audio-text representation learning.Dataset and demos are available at https://yyua8222.github.io/Sound-VECaps-demo/.

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 sound-tracks, 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/.

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modelling techniques to audio data. However, traditional codecs often operate at high bitrates or within narrow domains such as speech and lack the semantic clues required for efficient language modelling. Addressing these challenges, we introduce SemantiCodec, a novel codec designed to compress audio into fewer than a hundred tokens per second across diverse audio types, including speech, general sound, and music, without compromising quality. SemantiCodec features a dual-encoder architecture: a semantic encoder using a self-supervised pre-trained Audio Masked Autoencoder (AudioMAE), discretized using k-means clustering on extensive audio data, and an acoustic encoder to capture the remaining details. The semantic and acoustic encoder outputs are used to reconstruct audio via a diffusion-model-based decoder. SemantiCodec is presented in three variants with token rates of 25, 50, and 100 per second, supporting a range of ultra-low bit rates between 0.31 kbps and 1.40 kbps. Experimental results demonstrate that SemantiCodec significantly outperforms the state-of-the-art Descript codec on reconstruction quality. Our results also suggest that SemantiCodec contains significantly richer semantic information than all evaluated state-of-the-art audio codecs, even at significantly lower bitrates. Our code and demos are available at https://haoheliu.github.io/SemantiCodec/ .

Although audio generation shares commonalities across different types of audio, such as speech, music, and sound effects, designing models for each type requires careful consideration of specific objectives and biases that can significantly differ from those of other types. To bring us closer to a unified perspective of audio generation, this paper proposes a holistic framework that utilizes the same learning method for speech, music, and sound effect generation. Our framework utilizes a general representation of audio, called “language of audio” (LOA). Any audio can be translated into LOA based on AudioMAE, a self-supervised pre-trained representation learning model. In the generation process, we translate other modalities into LOA by using a GPT-2 model, and we perform self-supervised audio generation learning with a latent diffusion model conditioned on the LOA of audio in our training set. The proposed framework naturally brings advantages such as reusable self-supervised pretrained latent diffusion models. Experiments on the major benchmarks of text-to-audio, text-to-music, and text-to-speech with three AudioLDM 2 variants demonstrate competitive performance of the AudioLDM 2 framework against previous approaches.

Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA). LASS aims to separate a target sound from an audio mixture given a natural language query, which provides a natural and scalable interface for digital audio applications. Recent works on LASS, despite attaining promising separation performance on specific sources (e.g., musical instruments, limited classes of audio events), are unable to separate audio concepts in the open domain. In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries. We train AudioSep on large-scale multimodal datasets and extensively evaluate its capabilities on numerous tasks including audio event separation, musical instrument separation, and speech enhancement. AudioSep demonstrates strong separation performance and impressive zero-shot generalization ability using audio captions or text labels as queries, substantially outperforming previous audio-queried and language-queried sound separation models. For reproducibility of this work, we will release the source code, evaluation benchmark and pre-trained model at: https://github.com/Audio-AGI/AudioSep.

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 concate-nated 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.

Foley sound generation aims to synthesise the background sound for multimedia content. Previous models usually employ a large development set with labels as input (e.g., single numbers or one-hot vector). In this work, we propose a diffusion model based system for Foley sound generation with text conditions. To alleviate the data scarcity issue, our model is initially pre-trained with large-scale datasets and fine-tuned to this task via transfer learning using the contrastive language-audio pertaining (CLAP) technique. We have observed that the feature embedding extracted by the text encoder can significantly affect the performance of the generation model. Hence, we introduce a trainable layer after the encoder to improve the text embedding produced by the encoder. In addition, we further refine the generated waveform by generating multiple candidate audio clips simultaneously and selecting the best one, which is determined in terms of the similarity score between the embedding of the candidate clips and the embedding of the target text label. Using the proposed method, our system ranks \({1}^{st}\) among the systems submitted to DCASE Challenge 2023 Task 7. The results of the ablation studies illustrate that the proposed techniques significantly improve sound generation performance. The codes for implementing the proposed system are available online.

Foley sound presents the background sound for multimedia content and the generation of Foley sound involves computationally modelling sound effects with specialized techniques. In this work, we proposed a system for DCASE 2023 challenge task 7: Foley Sound Synthesis. The proposed system is based on AudioLDM, which is a diffusion-based text-to-audio generation model. To alleviate the data-hungry problem, the system first trained with large-scale datasets and then downstreamed into this DCASE task via transfer learning. Through experiments, we found out that the feature extracted by the encoder can significantly affect the performance of the generation model. Hence, we improve the results by leveraging the input label with related text embedding features obtained by a significant language model, i.e., contrastive language-audio pertaining (CLAP). In addition, we utilize a filtering strategy to further refine the output, i.e. by selecting the best results from the candidate clips generated in terms of the similarity score between the sound and target labels. The overall system achieves a Frechet audio distance (FAD) score of 4.765 on average among all seven different classes, substantially outperforming the baseline system which performs a FAD score of 9.7.

Despite recent progress in text-to-audio (TTA) generation, we show that the state-of-the-art models, such as AudioLDM, trained on datasets with an imbalanced class distribution, such as AudioCaps, are biased in their generation performance. Specifically, they excel in generating common audio classes while underperforming in the rare ones, thus degrading the overall generation performance. We refer to this problem as long-tailed text-to-audio generation. To address this issue, we propose a simple retrieval-augmented approach for TTA models. Specifically, given an input text prompt, we first leverage a Contrastive Language Audio Pretraining (CLAP) model to retrieve relevant text-audio pairs. The features of the retrieved audio-text data are then used as additional conditions to guide the learning of TTA models. We enhance AudioLDM with our proposed approach and denote the resulting augmented system as Re-AudioLDM. On the AudioCaps dataset, Re-AudioLDM achieves a state-of-the-art Frechet Audio Distance (FAD) of 1.37, outperforming the existing approaches by a large margin. Furthermore, we show that Re-AudioLDM can generate realistic audio for complex scenes, rare audio classes, and even unseen audio types, indicating its potential in TTA tasks.

Text-to-audio (TTA) system has recently gained attention for its ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computational costs. In this study, we propose AudioLDM, a TTA system that is built on a latent space to learn the continuous audio representations from contrastive language-audio pretraining (CLAP) latents. The pretrained CLAP models enable us to train LDMs with audio embedding while providing text embedding as a condition during sampling. By learning the latent representations of audio signals and their compositions without modeling the cross-modal relationship, AudioLDM is advantageous in both generation quality and computational efficiency. Trained on AudioCaps with a single GPU, AudioLDM achieves state-of-the-art TTA performance measured by both objective and subjective metrics (e.g., frechet distance). Moreover, AudioLDM is the first TTA system that enables various text-guided audio manipulations (e.g., style transfer) in a zero-shot fashion. Our implementation and demos are available at https://audioldm.github.io.

Large Language Models (LLMs) have shown great promise in integrating diverse expert models to tackle intricate language and vision tasks. Despite their significance in advancing the field of Artificial Intelligence Generated Content (AIGC), their potential in intelligent audio content creation remains unexplored. In this work, we tackle the problem of creating audio content with storylines encompassing speech, music, and sound effects, guided by text instructions. We present WavJourney, a system that leverages LLMs to connect various audio models for audio content generation. Given a text description of an auditory scene, WavJourney first prompts LLMs to generate a structured script dedicated to audio storytelling. The audio script incorporates diverse audio elements, organized based on their spatio-temporal relationships. As a conceptual representation of audio, the audio script provides an interactive and interpretable rationale for human engagement. Afterward, the audio script is fed into a script compiler, converting it into a computer program. Each line of the program calls a task-specific audio generation model or computational operation function (e.g., concatenate, mix). The computer program is then executed to obtain an explainable solution for audio generation. We demonstrate the practicality of WavJourney across diverse real-world scenarios, including science fiction, education, and radio play. The explainable and interactive design of WavJourney fosters human-machine co-creation in multi-round dialogues, enhancing creative control and adaptability in audio production. WavJourney audiolizes the human imagination, opening up new avenues for creativity in multimedia content creation.

Contrastive language-audio pretraining (CLAP) has been developed to align the representations of audio and language, achieving remarkable performance in retrieval and classification tasks. However, current CLAP struggles to capture temporal information within audio and text features, presenting substantial limitations for tasks such as audio retrieval and generation. To address this gap, we introduce T-CLAP, a temporal-enhanced CLAP model. We use Large Language Models (LLMs) and mixed-up strategies to generate temporal-contrastive captions for audio clips from extensive audio-text datasets. Subsequently, a new temporal-focused contrastive loss is designed to fine-tune the CLAP model by incorporating these synthetic data. We conduct comprehensive experiments and analysis in multiple downstream tasks. T-CLAP shows improved capability in capturing the temporal relationship of sound events and outperforms state-of-the-art models by a significant margin. Our code and models will be released soon.

Deep neural networks have recently achieved break-throughs in sound generation. Despite the outstanding sample quality, current sound generation models face issues on small-scale datasets (e.g., overfitting), significantly limiting performance. In this paper, we make the first attempt to investigate the benefits of pre-training on sound generation with AudioLDM, the cutting-edge model for audio generation, as the backbone. Our study demonstrates the advantages of the pre-trained AudioLDM, especially in data-scarcity scenarios. In addition, the baselines and evaluation protocol for sound generation systems are not consistent enough to compare different studies directly. Aiming to facilitate further study on sound generation tasks, we benchmark the sound generation task on various frequently-used datasets. We hope our results on transfer learning and benchmarks can provide references for further research on conditional sound generation.

Although audio generation shares commonalities across different types of audio, such as speech, music, and sound effects, designing models for each type requires careful consideration of specific objectives and biases that can significantly differ from those of other types. To bring us closer to a unified perspective of audio generation, this paper proposes a framework that utilizes the same learning method for speech, music, and sound effect generation. Our framework introduces a general representation of audio, called "language of audio" (LOA). Any audio can be translated into LOA based on AudioMAE, a self-supervised pre-trained representation learning model. In the generation process, we translate any modalities into LOA by using a GPT-2 model, and we perform self-supervised audio generation learning with a latent diffusion model conditioned on LOA. The proposed framework naturally brings advantages such as in-context learning abilities and reusable self-supervised pretrained AudioMAE and latent diffusion models. Experiments on the major benchmarks of text-to-audio, text-to-music, and text-to-speech demonstrate state-of-the-art or competitive performance against previous approaches. Our code, pretrained model, and demo are available at https://audioldm.github.io/audioldm2.

Sound Event Localization and Detection (SELD) is a task that involves detecting different types of sound events along with their temporal and spatial information, specifically, detecting the classes of events and estimating their corresponding direction of arrivals at each frame. In practice, real-world sound scenes might be complex as they may contain multiple overlapping events. For instance, in DCASE challenges task 3, each clip may involve simultaneous occurrences of up to five events. To handle multiple overlapping sound events, current methods prefer multiple output branches to estimate each event, which increases the size of the models. Therefore, current methods are often difficult to be deployed on the edge of sensor networks. In this paper, we propose a method called Probabilistic Localization and Detection of Independent Sound Events with Transformers (PLDISET), which estimates numerous events by using one output branch. The method has three stages. First, we introduce the track generation module to obtain various tracks from extracted features. Then, these tracks are fed into two transformers for sound event detection (SED) and localization, respectively. Finally, one output system, including a linear Gaussian system and regression network, is used to estimate each track. We give the evaluation resn results of our model on DCASE 2023 Task 3 development dataset.