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.

EDTC: enhance depth of text comprehension in automated audio captioning

Modality discrepancies have perpetually posed significant challenges within the realm of Automated Audio Captioning (AAC) and across all multi-modal domains. Facilitating models in comprehending text information plays a pivotal role in establishing a seamless connection between the two modalities of text and audio. While recent research has focused on closing the gap between these two modalities through contrastive learning, it is challenging to bridge the difference between both modalities using only simple contrastive loss. This paper introduces Enhance Depth of Text Comprehension (EDTC), which enhances the model's understanding of text information from three different perspectives. First, we propose a novel fusion module, FUSER, which aims to extract shared semantic information from different audio features through feature fusion. We then introduced TRANSLATOR, a novel alignment module designed to align audio features and text features along the tensor level. Finally, the weights are updated by adding momentum to the twin structure so that the model can learn information about both modalities at the same time. The resulting method achieves state-of-the-art performance on AudioCaps datasets and demonstrates results comparable to the state-of-the-art on Clotho datasets.

Selective-Memory Meta-Learning with Environment Representations for Sound Event Localization and Detection

Environment shifts and conflicts present significant challenges for learning-based sound event localization and detection (SELD) methods. SELD systems, when trained in particular acoustic settings, often show restricted generalization capabilities for diverse acoustic environments. Furthermore, it is notably costly to obtain annotated samples for spatial sound events. Deploying a SELD system in a new environment requires extensive time for re-training and fine-tuning. To overcome these challenges, we propose environment-adaptive Meta-SELD, designed for efficient adaptation to new environments using minimal data. Our method specifically utilizes computationally synthesized spatial data and employs Model-Agnostic Meta-Learning (MAML) on a pre-trained, environment-independent model. The method then utilizes fast adaptation to unseen real-world environments using limited samples from the respective environments. Inspired by the Learning-to-Forget approach, we introduce the concept of selective memory as a strategy for resolving conflicts across environments. This approach involves selectively memorizing target-environment-relevant information and adapting to the new environments through the selective attenuation of model parameters. In addition, we introduce environment representations to characterize different acoustic settings, enhancing the adaptability of our attenuation approach to various environments. We evaluate our proposed method on the development set of the Sony-TAU Realistic Spatial Soundscapes 2023 (STARSS23) dataset and computationally synthesized scenes. Experimental results demonstrate the superior performance of the proposed method compared to conventional supervised learning methods, particularly in localization.

Balanced SNR-Aware Distillation for Guided Text-to-Audio Generation

Diffusion models have demonstrated promising results in text-to-audio generation tasks. However, their practical usability is hindered by slow sampling speeds, limiting their applicability in high-throughput scenarios. To address this challenge, progressive distillation methods have been effective in producing more compact and efficient models. Nevertheless, these methods encounter issues with unbalanced weights at both high and low noise levels, potentially impacting the quality of generated samples. In this paper, we propose the adaptation of the progressive distillation method to text-to-audio generation tasks and introduce the Balanced SNR-Aware~(BSA) method, an enhanced loss-weighting mechanism for diffusion distillation. The BSA method employs a balanced approach to weight the loss for both high and low noise levels. We evaluate our proposed method on the AudioCaps dataset and report experimental results showing superior performance during the reverse diffusion process compared to previous distillation methods with the same number of sampling steps. Furthermore, the BSA method allows for a significant reduction in sampling steps from 200 to 25, with minimal performance degradation when compared to the original teacher models.

META-SELD: Meta-Learning for Fast Adaptation to the new environment in Sound Event Localization and Detection

For learning-based sound event localization and detection (SELD) methods, different acoustic environments in the training and test sets may result in large performance differences in the validation and evaluation stages. Different environments, such as different sizes of rooms, different reverberation times, and different background noise, may be reasons for a learning-based system to fail. On the other hand, acquiring annotated spatial sound event samples, which include onset and offset time stamps, class types of sound events, and direction-of-arrival (DOA) of sound sources is very expensive. In addition, deploying a SELD system in a new environment often poses challenges due to time-consuming training and fine-tuning processes. To address these issues, we propose Meta-SELD, which applies meta-learning methods to achieve fast adaptation to new environments. More specifically, based on Model Agnostic Meta-Learning (MAML), the proposed Meta-SELD aims to find good meta-initialized parameters to adapt to new environments with only a small number of samples and parameter updating iterations. We can then quickly adapt the meta-trained SELD model to unseen environments. Our experiments compare fine-tuning methods from pre-trained SELD models with our Meta-SELD on the Sony-TAU Realistic Spatial Soundscapes 2023 (STARSSS23) dataset. The evaluation results demonstrate the effectiveness of Meta-SELD when adapting to new environments.

WavJourney: Compositional Audio Creation with Large Language Models

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.

Sound Event Localization and Detection for Real Spatial Sound Scenes: Event-Independent Network and Data Augmentation Chains

Sound event localization and detection (SELD) is a joint task of sound event detection and direction-of-arrival estimation. In DCASE 2022 Task 3, types of data transform from computationally generated spatial recordings to recordings of real-sound scenes. Our system submitted to the DCASE 2022 Task 3 is based on our previous proposed Event-Independent Network V2 (EINV2) with a novel data augmentation method. Our method employs EINV2 with a track-wise output format, permutation-invariant training, and a soft parameter-sharing strategy, to detect different sound events of the same class but in different locations. The Conformer structure is used for extending EINV2 to learn local and global features. A data augmentation method, which contains several data augmentation chains composed of stochastic combinations of several different data augmentation operations, is utilized to generalize the model. To mitigate the lack of real-scene recordings in the development dataset and the presence of sound events being unbalanced, we exploit FSD50K, AudioSet, and TAU Spatial Room Impulse Response Database (TAU-SRIR DB) to generate simulated datasets for training. We present results on the validation set of Sony-TAu Realistic Spatial Soundscapes 2022 (STARSS22) in detail. Experimental results indicate that the ability to generalize to different environments and unbalanced performance among different classes are two main challenges. We evaluate our proposed method in Task 3 of the DCASE 2022 challenge and obtain the second rank in the teams ranking. Source code is released.

A Track-Wise Ensemble Event Independent Network for Polyphonic Sound Event Localization and Detection

Polyphonic sound event localization and detection (SELD) aims at detecting types of sound events with corresponding temporal activities and spatial locations. In this paper, a track-wise ensemble event independent network with a novel data augmentation method is proposed. The proposed model is based on our previous proposed Event-Independent Network V2 and is extended by conformer blocks and dense blocks. The track-wise ensemble model with track-wise output format is proposed to solve an ensemble model problem for track-wise output format that track permutation may occur among different models. The data augmentation approach contains several data augmentation chains, which are composed of random combinations of several data augmentation operations. The method also utilizes log-mel spectrograms, intensity vectors, and Spatial Cues-Augmented Log-Spectrogram (SALSA) for different models. We evaluate our proposed method in the Task of the L3DAS22 challenge and obtain the top ranking solution with a location-dependent F-score to be 0.699. Source code is released.

ARCA23K: An audio dataset for investigating open-set label noise

The availability of audio data on sound sharing platforms such as Freesound gives users access to large amounts of annotated audio. Utilising such data for training is becoming increasingly popular, but the problem of label noise that is often prevalent in such datasets requires further investigation. This paper introduces ARCA23K, an Automatically Retrieved and Curated Audio dataset comprised of over 23000 labelled Freesound clips. Unlike past datasets such as FSDKaggle2018 and FSDnoisy18K, ARCA23K facilitates the study of label noise in a more controlled manner. We describe the entire process of creating the dataset such that it is fully reproducible, meaning researchers can extend our work with little effort. We show that the majority of labelling errors in ARCA23K are due to out-of-vocabulary audio clips, and we refer to this type of label noise as open-set label noise. Experiments are carried out in which we study the impact of label noise in terms of classification performance and representation learning.

Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation

Deep neural network based methods have been successfully applied to music source separation. They typically learn a mapping from a mixture spectrogram to a set of source spectrograms, all with magnitudes only. This approach has several limitations: 1) its incorrect phase reconstruction degrades the performance, 2) it limits the magnitude of masks between 0 and 1 while we observe that 22% of time-frequency bins have ideal ratio mask values of over~1 in a popular dataset, MUSDB18, 3) its potential on very deep architectures is under-explored. Our proposed system is designed to overcome these. First, we propose to estimate phases by estimating complex ideal ratio masks (cIRMs) where we decouple the estimation of cIRMs into magnitude and phase estimations. Second, we extend the separation method to effectively allow the magnitude of the mask to be larger than 1. Finally, we propose a residual UNet architecture with up to 143 layers. Our proposed system achieves a state-of-the-art MSS result on the MUSDB18 dataset, especially, a SDR of 8.98~dB on vocals, outperforming the previous best performance of 7.24~dB. The source code is available at: https://github.com/bytedance/music_source_separation