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 2102.09114cs.CL
收藏

回声状态语音识别

Echo State Speech Recognition

Google(谷歌)

Harsh Shrivastava, Ankush Garg, Yuan Cao, Yu Zhang, Tara Sainath

摘要:

我们提出了自动语音识别(ASR)模型的回声状态网络(ESN)的启发,其中模型中的递归神经网络(RNN)层的子集是随机初始化和未经训练的。我们的研究集中在RNN-T和Conformer模型上,我们证明了即使解码器完全随机化,模型质量也不会下降。此外,这样的模型可以更有效地训练,因为解码器不需要更新。相比之下,随机化编码器会损害模型质量,这表明优化编码器和学习声学输入的正确表示对于语音识别更重要。总的来说,我们挑战了为所有组件训练ASR模型的常见做法,并证明了基于ESN的模型可以同样出色地执行,但比完全可训练的模型能够实现更有效的训练和存储。

英文摘要:

We propose automatic speech recognition (ASR) models inspired by echo state network (ESN), in which a subset of recurrent neural networks (RNN) layers in the models are randomly initialized and untrained. Our study focuses on RNN-T and Conformer models, and we show that model quality does not drop even when the decoder is fully randomized. Furthermore, such models can be trained more efficiently as the decoders do not require to be updated. By contrast, randomizing encoders hurts model quality, indicating that optimizing encoders and learn proper representations for acoustic inputs are more vital for speech recognition. Overall, we challenge the common practice of training ASR models for all components, and demonstrate that ESN-based models can perform equally well but enable more efficient training and storage than fully-trainable counterparts.

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。

↑