Weakly-supervised learning has emerged as a promising approach to leverage limited labeled data in various domains by bridging the gap between fully supervised methods and unsupervised techniques. Acquisition of strong annotations for detecting sound events is prohibitively expensive, making weakly supervised learning a more cost-effective and broadly applicable alternative. In order to enhance the recognition rate of the learning of detection of weakly-supervised sound events, we introduce a Frame Pairwise Distance (FPD) loss branch, complemented with a minimal amount of synthesized data. The corresponding sampling and label processing strategies are also proposed. Two distinct distance metrics are employed to evaluate the proposed approach. Finally, the method is validated on the standard DCASE dataset. The obtained experimental results corroborated the efficacy of this approach.
Contrastive Language-Audio Pretraining (CLAP) is pre-trained to associate audio features with human language, making it a natural zero-shot classifier to recognize unseen sound categories. To adapt CLAP to downstream tasks, prior works inevitably require labeled domain audios, which limits their scalability under data scarcity and deprives them of the capability to detect novel classes as the original CLAP. In this work, by leveraging the modality alignment in CLAP, we propose an efficient audio-free prompt tuning scheme aimed at optimizing a few prompt tokens from texts instead of audios, which regularizes the model space to avoid overfitting the seen classes as well. Based on this, a multi-grained prompt design is further explored to fuse global and local information. Experiments on several tasks demonstrate that our approach can boost the CLAP and outperform other training methods on model performance and training efficiency. While conducting zero-shot inference on unseen categories, it still shows better transferability than the vanilla CLAP. Moreover, our method is flexible enough even if only knowing the downstream class names. The code will be released soon.
Learning meaningful frame-wise features on a partially labeled dataset is crucial to semi-supervised sound event detection. Prior works either maintain consistency on frame-level predictions or seek feature-level similarity among neighboring frames, which cannot exploit the potential of unlabeled data. In this work, we design a Local and Global Consistency (LGC) regularization scheme to enhance the model on both label- and feature-level. The audio CutMix is introduced to change the contextual information of clips. Then, the local consistency is adopted to encourage the model to leverage local features for frame-level predictions, and the global consistency is applied to force features to align with global prototypes through a specially designed contrastive loss. Experiments on the DESED dataset indicate the superiority of LGC, surpassing its respective competitors largely with the same settings as the baseline system. Besides, combining LGC with existing methods can obtain further improvements. The code will be released soon.
Text-based audio generation models have limitations as they cannot encompass all the information in audio, leading to restricted controllability when relying solely on text. To address this issue, we propose a novel model that enhances the controllability of existing pre-trained text-to-audio models by incorporating additional conditions including content (timestamp) and style (pitch contour and energy contour) as supplements to the text. This approach achieves fine-grained control over the temporal order, pitch, and energy of generated audio. To preserve the diversity of generation, we employ a trainable control condition encoder that is enhanced by a large language model and a trainable Fusion-Net to encode and fuse the additional conditions while keeping the weights of the pre-trained text-to-audio model frozen. Due to the lack of suitable datasets and evaluation metrics, we consolidate existing datasets into a new dataset comprising the audio and corresponding conditions and use a series of evaluation metrics to evaluate the controllability performance. Experimental results demonstrate that our model successfully achieves fine-grained control to accomplish controllable audio generation. Audio samples and our dataset are publicly available at https://conditionaudiogen.github.io/conditionaudiogen/
Recently, the ability of language models (LMs) has attracted increasing attention in visual cross-modality. In this paper, we further explore the generation capacity of LMs for sound event detection (SED), beyond the visual domain. Specifically, we propose an elegant method that aligns audio features and text features to accomplish sound event classification and temporal location. The framework consists of an acoustic encoder, a contrastive module that align the corresponding representations of the text and audio, and a decoupled language decoder that generates temporal and event sequences from the audio characteristic. Compared with conventional works that require complicated processing and barely utilize limited audio features, our model is more concise and comprehensive since language model directly leverage its semantic capabilities to generate the sequences. We investigate different decoupling modules to demonstrate the effectiveness for timestamps capture and event classification. Evaluation results show that the proposed method achieves accurate sequences of sound event detection.
The significance of multi-scale features has been gradually recognized by the edge detection community. However, the fusion of multi-scale features increases the complexity of the model, which is not friendly to practical application. In this work, we propose a Compact Twice Fusion Network (CTFN) to fully integrate multi-scale features while maintaining the compactness of the model. CTFN includes two lightweight multi-scale feature fusion modules: a Semantic Enhancement Module (SEM) that can utilize the semantic information contained in coarse-scale features to guide the learning of fine-scale features, and a Pseudo Pixel-level Weighting (PPW) module that aggregate the complementary merits of multi-scale features by assigning weights to all features. Notwithstanding all this, the interference of texture noise makes the correct classification of some pixels still a challenge. For these hard samples, we propose a novel loss function, coined Dynamic Focal Loss, which reshapes the standard cross-entropy loss and dynamically adjusts the weights to correct the distribution of hard samples. We evaluate our method on three datasets, i.e., BSDS500, NYUDv2, and BIPEDv2. Compared with state-of-the-art methods, CTFN achieves competitive accuracy with less parameters and computational cost. Apart from the backbone, CTFN requires only 0.1M additional parameters, which reduces its computation cost to just 60% of other state-of-the-art methods. The codes are available at https://github.com/Li-yachuan/CTFN-pytorch-master.
In this paper, we describe in detail our system for DCASE 2022 Task4. The system combines two considerably different models: an end-to-end Sound Event Detection Transformer (SEDT) and a frame-wise model, Metric Learning and Focal Loss CNN (MLFL-CNN). The former is an event-wise model which learns event-level representations and predicts sound event categories and boundaries directly, while the latter is based on the widely adopted frame-classification scheme, under which each frame is classified into event categories and event boundaries are obtained by post-processing such as thresholding and smoothing. For SEDT, self-supervised pre-training using unlabeled data is applied, and semi-supervised learning is adopted by using an online teacher, which is updated from the student model using the Exponential Moving Average (EMA) strategy and generates reliable pseudo labels for weakly-labeled and unlabeled data. For the frame-wise model, the ICT-TOSHIBA system of DCASE 2021 Task 4 is used. Experimental results show that the hybrid system considerably outperforms either individual model and achieves psds1 of 0.420 and psds2 of 0.783 on the validation set without external data. The code is available at https://github.com/965694547/Hybrid-system-of-frame-wise-model-and-SEDT.
Recently, an event-based end-to-end model (SEDT) has been proposed for sound event detection (SED) and achieves competitive performance. However, compared with the frame-based model, it requires more training data with temporal annotations to improve the localization ability. Synthetic data is an alternative, but it suffers from a great domain gap with real recordings. Inspired by the great success of UP-DETR in object detection, we propose to self-supervisedly pre-train SEDT (SP-SEDT) by detecting random patches (only cropped along the time axis). Experiments on the DCASE2019 task4 dataset show the proposed SP-SEDT can outperform fine-tuned frame-based model. The ablation study is also conducted to investigate the impact of different loss functions and patch size.
Sound event detection (SED) has gained increasing attention with its wide application in surveillance, video indexing, etc. Existing models in SED mainly generate frame-level predictions, converting it into a sequence multi-label classification problem, which inevitably brings a trade-off between event boundary detection and audio tagging when using weakly labeled data to train the model. Besides, it needs post-processing and cannot be trained in an end-to-end way. This paper firstly presents the 1D Detection Transformer (1D-DETR), inspired by Detection Transformer. Furthermore, given the characteristics of SED, the audio query and a one-to-many matching strategy for fine-tuning the model are added to 1D-DETR to form the model of Sound Event Detection Transformer (SEDT), which generates event-level predictions, end-to-end detection. Experiments are conducted on the URBAN-SED dataset and the DCASE2019 Task4 dataset, and both experiments have achieved competitive results compared with SOTA models. The application of SEDT on SED shows that it can be used as a framework for one-dimensional signal detection and may be extended to other similar tasks.
The recently proposed Mean Teacher has achieved state-of-the-art results in several semi-supervised learning benchmarks. The Mean Teacher method can exploit large-scale unlabeled data in a self-ensembling manner. In this paper, an effective Couple Learning method based on a well-trained model and a Mean Teacher model is proposed. The proposed pseudo-labels generated model (PLG) can increase strongly-labeled data and weakly-labeled data to improve performance of the Mean Teacher method. The Mean Teacher method can suppress noise in pseudo-labels data. The Couple Learning method can extract more information in the compound training data. These experimental results on Task 4 of the DCASE2020 challenge demonstrate the superiority of the proposed method, achieving about 39.18% F1-score on public eval set, outperforming 37.12% of the baseline system by a significant margin.