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 2406.02565cs.SDcs.CLcs.MAeess.AS
收藏

点对点学习中的序列到序列模型:一项实际应用

Sequence-to-sequence models in peer-to-peer learning: A practical application

Faculty of Informatics Juraj Dobrila University of Pula(伊斯特拉大学普拉分校信息学院);Faculty of Informatics and Digital Technologies University of Rijeka(里耶卡大学信息与数字技术学院)

Robert Šajina, Ivo Ipšić

AI总结:

本文研究了基于LSTM的Seq2Seq模型在点对点学习环境中的ASR任务适用性,实验表明该方法虽比集中式训练的WER略高,但在去中心化场景中具有可行性。

摘要:

本文探讨了基于LSTM单元的序列到序列(Seq2Seq)模型在点对点学习环境中用于自动语音识别(ASR)任务的适用性。利用两种不同的点对点学习方法,该研究模拟了智能体的学习过程,并使用两个不同的ASR数据集评估了它们在ASR任务中的性能。在集中式训练设置中,利用Deep Speech 2模型的缩小变体,单个模型在UserLibri数据集上训练时达到了84%的词错率(WER),在LJ Speech数据集上训练时达到了38%。相反,在涉及55个智能体的点对点学习场景中,UserLibri数据集的WER范围为87%至92%,LJ Speech数据集的WER范围为52%至56%。研究结果表明,在去中心化环境中采用Seq2Seq模型是可行的,尽管与集中式训练方法相比,其词错率(WER)略高。

英文摘要:

This paper explores the applicability of sequence-to-sequence (Seq2Seq) models based on LSTM units for Automatic Speech Recognition (ASR) task within peer-to-peer learning environments. Leveraging two distinct peer-to-peer learning methods, the study simulates the learning process of agents and evaluates their performance in ASR task using two different ASR datasets. In a centralized training setting, utilizing a scaled-down variant of the Deep Speech 2 model, a single model achieved a Word Error Rate (WER) of 84\% when trained on the UserLibri dataset, and 38\% when trained on the LJ Speech dataset. Conversely, in a peer-to-peer learning scenario involving 55 agents, the WER ranged from 87\% to 92\% for the UserLibri dataset, and from 52\% to 56\% for the LJ Speech dataset. The findings demonstrate the feasibility of employing Seq2Seq models in decentralized settings, albeit with slightly higher Word Error Rates (WER) compared to centralized training methods.

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。

↑