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 2210.16643cs.CLcs.AIcs.SDeess.AS
收藏

XNOR-FORMER:学习长语音中的精确近似Transformers

XNOR-FORMER: Learning Accurate Approximations in Long Speech Transformers

Carnegie Mellon University(卡内基梅隆大学)

Roshan Sharma, Bhiksha Raj

摘要:

Transformers是语音、视觉和自然语言处理等领域中许多任务的最新技术。自注意力是这种性能的关键贡献者,具有二次计算复杂性,这使得在更长的输入序列上训练具有挑战性。先前的工作已经产生了具有线性注意力的最先进的Transformer变体,然而,当前的模型牺牲性能以实现高效的实现。在这项工作中,我们开发了一种新的线性Transformer通过检查的自我关注内的关键查询产品的属性。我们的模型在语音识别和语音摘要方面优于最先进的方法,导致Librispeech-100语音识别基准和新的INTERVIEW语音识别基准的绝对WER提高了1%,并且对于使用How2的摘要,ROUGE提高了5分。

英文摘要:

Transformers are among the state of the art for many tasks in speech, vision, and natural language processing, among others. Self-attentions, which are crucial contributors to this performance have quadratic computational complexity, which makes training on longer input sequences challenging. Prior work has produced state-of-the-art transformer variants with linear attention, however, current models sacrifice performance to achieve efficient implementations. In this work, we develop a novel linear transformer by examining the properties of the key-query product within self-attentions. Our model outperforms state of the art approaches on speech recognition and speech summarization, resulting in 1 % absolute WER improvement on the Librispeech-100 speech recognition benchmark and a new INTERVIEW speech recognition benchmark, and 5 points on ROUGE for summarization with How2.

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。

↑