arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.02053eess.AS
收藏

使用随机分类器的小样本类别增量音频分类

Few-shot Class-incremental Audio Classification Using Stochastic Classifier

Yanxiong Li, Wenchang Cao, Jialong Li, Wei Xie, Qianhua He

AI总结:

针对类别持续增加导致音频分类模型需反复重训的问题,提出由冻结嵌入提取器和增量扩展随机分类器组成的小样本类别增量方法,并在 NS-100、LS-100 上优于四个基线。

摘要:

当前的音频分类方法通常假设类别数量是固定的,模型只能识别预先给定的类别。当新类别出现时,需要使用所有类别的充足样本重新训练模型。如果新类别不断出现,这些方法将无法良好运行,甚至不可行。在本研究中,我们提出了一种用于小样本类别增量音频分类的方法,能够持续识别新类别并记住旧类别。所提出的模型由嵌入提取器和随机分类器组成。前者在基础会话中训练,并在增量会话中冻结,而后者在所有会话中进行增量扩展。通过分别从 NSynth 和 LibriSpeech 音频语料库中选取样本,构建了两个数据集(NS-100 和 LS-100)。结果表明,我们的方法在平均准确率和性能下降率方面优于四个基线方法。代码位于 https://github.com/vinceasvp/meta-sc。

英文摘要:

It is generally assumed that number of classes is fixed in current audio classification methods, and the model can recognize pregiven classes only. When new classes emerge, the model needs to be retrained with adequate samples of all classes. If new classes continually emerge, these methods will not work well and even infeasible. In this study, we propose a method for fewshot class-incremental audio classification, which continually recognizes new classes and remember old ones. The proposed model consists of an embedding extractor and a stochastic classifier. The former is trained in base session and frozen in incremental sessions, while the latter is incrementally expanded in all sessions. Two datasets (NS-100 and LS-100) are built by choosing samples from audio corpora of NSynth and LibriSpeech, respectively. Results show that our method exceeds four baseline ones in average accuracy and performance dropping rate. Code is at https://github.com/vinceasvp/meta-sc.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑