AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models

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.

Transferable Selective Virtual Sensing Active Noise Control Technique Based on Metric Learning

Virtual sensing (VS) technology enables active noise control (ANC) systems to attenuate noise at virtual locations distant from the physical error microphones. Appropriate auxiliary filters (AF) can significantly enhance the effectiveness of VS approaches. The selection of appropriate AF for various types of noise can be automatically achieved using convolutional neural networks (CNNs). However, training the CNN model for different ANC systems is often labour-intensive and time-consuming. To tackle this problem, we propose a novel method, Transferable Selective VS, by integrating metric-learning technology into CNN-based VS approaches. The Transferable Selective VS method allows a pre-trained CNN to be applied directly to new ANC systems without requiring retraining, and it can handle unseen noise types. Numerical simulations demonstrate the effectiveness of the proposed method in attenuating sudden-varying broadband noises and real-world noises.

Latent Diffusion Model-Enabled Real-Time Semantic Communication Considering Semantic Ambiguities and Channel Noises

Semantic communication (SemCom) has emerged as a new paradigm for communication systems, with deep learning (DL) models being one of the key drives to shift from the accuracy of bit/symbol to the semantics and pragmatics of data. Nevertheless, DL-based SemCom systems often face performance bottlenecks due to overfitting, poor generalization, and sensitivity to outliers. Furthermore, the varying-fading gains and noises with uncertain signal-to-noise ratios (SNRs) commonly present in wireless channels usually restrict the accuracy of semantic information transmission. Consequently, to address the aforementioned issues, this paper constructs a SemCom system based on the latent diffusion model, and proposes three improvements compared to existing works: i) To handle potential outliers in the source data, semantic errors obtained by projected gradient descent based on the vulnerabilities of DL models, are utilized to update the parameters and obtain an outlier-robust encoder. ii) A lightweight single-layer latent space transformation adapter completes one-shot learning at transmitter and is placed before the decoder at receiver, enabling adaptation for out-of-distribution data or enhancing human-perceptual quality. iii) An end-to-end consistency distillation (EECD) strategy is used to distill the diffusion models trained in latent space, enabling deterministic single or few-step real-time denoising in various noisy channels while maintaining high semantic quality. Extensive numerical experiments across different datasets demonstrate the superiority of the proposed SemCom system, consistently proving its robustness to outliers, the capability to transmit data with unknown distributions, and the ability to perform real-time channel denoising tasks while preserving high human perceptual quality, outperforming the existing denoising approaches in semantic metrics such as MS-SSIM and LPIPS.

Computation-efficient Virtual Sensing Approach with Multichannel Adjoint Least Mean Square Algorithm

Multichannel active noise control (ANC) systems are designed to create a large zone of quietness (ZoQ) around the error microphones, however, the placement of these microphones often presents challenges due to physical limitations. Virtual sensing technique that effectively suppresses the noise far from the physical error microphones is one of the most promising solutions. Nevertheless, the conventional multichannel virtual sensing ANC (MVANC) system based on the multichannel filtered reference least mean square (MCFxLMS) algorithm often suffers from high computational complexity. This paper proposes a feedforward MVANC system that incorporates the multichannel adjoint least mean square (MCALMS) algorithm to overcome these limitations effectively. Computational analysis demonstrates the improvement of computational efficiency and numerical simulations exhibit comparable noise reduction performance at virtual locations compared to the conventional MCFxLMS algorithm. Additionally, the effects of varied tuning noises on system performance are also investigated, providing insightful findings on optimizing MVANC systems.

A Survey of Integrating Wireless Technology into Active Noise Control

Active Noise Control (ANC) is a widely adopted technology for reducing environmental noise across various scenarios. This paper focuses on enhancing noise reduction performance, particularly through the refinement of signal quality fed into ANC systems. We discuss the main wireless technique integrated into the ANC system, equipped with some innovative algorithms, in diverse environments. Instead of using microphone arrays, which increase the computation complexity of the ANC system, to isolate multiple noise sources to improve noise reduction performance, the application of the wireless technique avoids extra computation demand. Wireless transmissions of reference, error, and control signals are also applied to improve the convergence performance of the ANC system. Furthermore, this paper lists some wireless ANC applications, such as earbuds, headphones, windows, and headrests, underscoring their adaptability and efficiency in various settings.

Unsupervised learning based end-to-end delayless generative fixed-filter active noise control

Delayless noise control is achieved by our earlier generative fixed-filter active noise control (GFANC) framework through efficient coordination between the co-processor and real-time controller. However, the one-dimensional convolutional neural network (1D CNN) in the co-processor requires initial training using labelled noise datasets. Labelling noise data can be resource-intensive and may introduce some biases. In this paper, we propose an unsupervised-GFANC approach to simplify the 1D CNN training process and enhance its practicality. During training, the co-processor and real-time controller are integrated into an end-to-end differentiable ANC system. This enables us to use the accumulated squared error signal as the loss for training the 1D CNN. With this unsupervised learning paradigm, the unsupervised-GFANC method not only omits the labelling process but also exhibits better noise reduction performance compared to the supervised GFANC method in real noise experiments.

Description on IEEE ICME 2024 Grand Challenge: Semi-supervised Acoustic Scene Classification under Domain Shift

Acoustic scene classification (ASC) is a crucial research problem in computational auditory scene analysis, and it aims to recognize the unique acoustic characteristics of an environment. One of the challenges of the ASC task is domain shift caused by a distribution gap between training and testing data. Since 2018, ASC challenges have focused on the generalization of ASC models across different recording devices. Although this task in recent years has achieved substantial progress in device generalization, the challenge of domain shift between different regions, involving characteristics such as time, space, culture, and language, remains insufficiently explored at present. In addition, considering the abundance of unlabeled acoustic scene data in the real world, it is important to study the possible ways to utilize these unlabelled data. Therefore, we introduce the task Semi-supervised Acoustic Scene Classification under Domain Shift in the ICME 2024 Grand Challenge. We encourage participants to innovate with semi-supervised learning techniques, aiming to develop more robust ASC models under domain shift.

Sub-band and Full-band Interactive U-Net with DPRNN for Demixing Cross-talk Stereo Music

This paper presents a detailed description of our proposed methods for the ICASSP 2024 Cadenza Challenge. Experimental results show that the proposed system can achieve better performance than official baselines.

A Comprehensive End-to-End Computer Vision Framework for Restoration and Recognition of Low-Quality Engineering Drawings

The digitization of engineering drawings is crucial for efficient reuse, distribution, and archiving. Existing computer vision approaches for digitizing engineering drawings typically assume the input drawings have high quality. However, in reality, engineering drawings are often blurred and distorted due to improper scanning, storage, and transmission, which may jeopardize the effectiveness of existing approaches. This paper focuses on restoring and recognizing low-quality engineering drawings, where an end-to-end framework is proposed to improve the quality of the drawings and identify the graphical symbols on them. The framework uses K-means clustering to classify different engineering drawing patches into simple and complex texture patches based on their gray level co-occurrence matrix statistics. Computer vision operations and a modified Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) model are then used to improve the quality of the two types of patches, respectively. A modified Faster Region-based Convolutional Neural Network (Faster R-CNN) model is used to recognize the quality-enhanced graphical symbols. Additionally, a multi-stage task-driven collaborative learning strategy is proposed to train the modified ESRGAN and Faster R-CNN models to improve the resolution of engineering drawings in the direction that facilitates graphical symbol recognition, rather than human visual perception. A synthetic data generation method is also proposed to construct quality-degraded samples for training the framework. Experiments on real-world electrical diagrams show that the proposed framework achieves an accuracy of 98.98% and a recall of 99.33%, demonstrating its superiority over previous approaches. Moreover, the framework is integrated into a widely-used power system software application to showcase its practicality.

Interactive Dual-Conformer with Scene-Inspired Mask for Soft Sound Event Detection

Traditional binary hard labels for sound event detection (SED) lack details about the complexity and variability of sound event distributions. Recently, a novel annotation workflow is proposed to generate fine-grained non-binary soft labels, resulting in a new real-life dataset named MAESTRO Real for SED. In this paper, we first propose an interactive dual-conformer (IDC) module, in which a cross-interaction mechanism is applied to effectively exploit the information from soft labels. In addition, a novel scene-inspired mask (SIM) based on soft labels is incorporated for more precise SED predictions. The SIM is initially generated through a statistical approach, referred as SIM-V1. However, the fixed artificial mask may mismatch the SED model, resulting in limited effectiveness. Therefore, we further propose SIM-V2, which employs a word embedding model for adaptive SIM estimation. Experimental results show that the proposed IDC module can effectively utilize the information from soft labels, and the integration of SIM-V1 can further improve the accuracy. In addition, the impact of different word embedding dimensions on SIM-V2 is explored, and the results show that the appropriate dimension can enable SIM-V2 achieve superior performance than SIM-V1. In DCASE 2023 Challenge Task4B, the proposed system achieved the top ranking performance on the evaluation dataset of MAESTRO Real.