arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.14764eess.AS
收藏

基于Transformer的端到端语音识别中的有效解码器掩蔽

Effective Decoder Masking for Transformer Based End-to-End Speech Recognition

Shi-Yan Weng, Berlin Chen

摘要:

基于注意力的编码器-解码器建模范例在诸如自动语音识别(ASR)、文本到语音(TTS)等的各种语音处理任务上取得了有希望的结果。这种范式利用神经网络的泛化能力来学习从输入序列到输出序列的直接映射,而不依赖于诸如音频文本对齐或发音词典之类的先验知识。然而,源于这种范式的ASR模型容易过拟合,特别是当训练数据有限时。受SpecAugment和BERT类掩码语言建模的启发,本文提出了一种基于解码器掩码的端到端(E2 E)ASR模型训练方法。在训练阶段,我们用符号[mask]随机替换解码器历史文本输入的某些部分,以鼓励解码器鲁棒地输出正确的令牌,即使其解码历史的一部分被屏蔽或损坏。所提出的方法实例化与顶级的线变压器为基础的E2 E ASR模型。在Librispeech 960 h和TedLium 2基准数据集上进行的大量实验表明,与现有的一些强E2 E ASR系统相比,我们的方法具有优越的性能。

英文摘要:

The attention-based encoder-decoder modeling paradigm has achieved promising results on a variety of speech processing tasks like automatic speech recognition (ASR), text-to-speech (TTS) and among others. This paradigm takes advantage of the generalization ability of neural networks to learn a direct mapping from an input sequence to an output sequence, without recourse to prior knowledge such as audio-text alignments or pronunciation lexicons. However, ASR models stemming from this paradigm are prone to overfitting, especially when the training data is limited. Inspired by SpecAugment and BERT-like masked language modeling, we propose in the paper a decoder masking based training approach for end-to-end (E2E) ASR models. During the training phase we randomly replace some portions of the decoder's historical text input with the symbol [mask], in order to encourage the decoder to robustly output a correct token even when parts of its decoding history are masked or corrupted. The proposed approach is instantiated with the top-of-the-line transformer-based E2E ASR model. Extensive experiments on the Librispeech960h and TedLium2 benchmark datasets demonstrate the superior performance of our approach in comparison to some existing strong E2E ASR systems.

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。

↑