Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2103.16079

Environmental sound analysis with mixup based multitask learning and cross-task fusion

Weiping Zheng·Dacan Jiang·Gansen Zhao
View original source ↗Read source document ↗Export metadata ↓

Abstract

Environmental sound analysis is currently getting more and more attentions. In the domain, acoustic scene classification and acoustic event classification are two closely related tasks. In this letter, a two-stage method is proposed for the above tasks. In the first stage, a mixup based MTL solution is proposed to classify both tasks in one single convolutional neural network. Artificial multi-label samples are used in the training of the MTL model, which are mixed up using existing single-task datasets. The multi-task model obtained can effectively recognize both the acoustic scenes and events. Compared with other methods such as re-annotation or synthesis, the mixup based MTL is low-cost, flexible and effective. In the second stage, the MTL model is modified into a single-task model which is fine-tuned using the original dataset corresponding to the specific task. By controlling the frozen layers carefully, the task-specific high level features are fused and the performance of the single classification task is further improved. The proposed method has confirmed the complementary characteristics of acoustic scene and acoustic event classifications. Finally, enhanced by ensemble learning, a satisfactory accuracy of 84.5 percent on TUT acoustic scene 2017 dataset and an accuracy of 77.5 percent on ESC-50 dataset are achieved respectively.

Explore related subjects

cs.SDcs.CVcs.MMeess.AS

Keep this discovery

BibTeXRIS

Weiping Zheng, Dacan Jiang, Gansen Zhao. 2021-03-30. Environmental sound analysis with mixup based multitask learning and cross-task fusion. https://arxiv.org/abs/2103.16079

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗