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 2203.00613cs.CLcs.LGcs.SDeess.AS
收藏

面向通用语音分析引擎的研究

Towards a Common Speech Analysis Engine

IBM Research AI(IBM研究院人工智能);Technion - Israel Institute of Technology(以色列理工学院)

Hagai Aronowitz, Itai Gat, Edmilson Morais, Weizhong Zhu, Ron Hoory

摘要:

自我监督表示学习的最新创新导致了自然语言处理的显著进步。也就是说,在语音处理领域,基于自监督表示学习的系统还没有被认为是最先进的。我们建议利用基于自监督的语音处理的最新进展来创建一个通用的语音分析引擎。这样的引擎应该能够使用单个架构处理多个语音处理任务,以获得最先进的准确性。该引擎还必须支持具有小训练数据集的新任务。除此之外,通用引擎应该能够支持使用客户内部私有数据的分布式训练。我们提出了一个共同的语音分析引擎的基础上的HuBERT自监督语音表示的架构。在实验的基础上,我们报告了我们的语言识别和情感识别的标准评估NIST-LRE 07和IEMOCAP的结果。我们的结果超过了迄今为止在这些任务上报告的最先进的性能。我们还分析了我们的引擎在情感识别任务中使用减少量的训练数据,并展示了如何实现改进的结果。

英文摘要:

Recent innovations in self-supervised representation learning have led to remarkable advances in natural language processing. That said, in the speech processing domain, self-supervised representation learning-based systems are not yet considered state-of-the-art. We propose leveraging recent advances in self-supervised-based speech processing to create a common speech analysis engine. Such an engine should be able to handle multiple speech processing tasks, using a single architecture, to obtain state-of-the-art accuracy. The engine must also enable support for new tasks with small training datasets. Beyond that, a common engine should be capable of supporting distributed training with client in-house private data. We present the architecture for a common speech analysis engine based on the HuBERT self-supervised speech representation. Based on experiments, we report our results for language identification and emotion recognition on the standard evaluations NIST-LRE 07 and IEMOCAP. Our results surpass the state-of-the-art performance reported so far on these tasks. We also analyzed our engine on the emotion recognition task using reduced amounts of training data and show how to achieve improved results.

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。

↑