arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.06239eess.AScs.CLcs.SD
收藏

汉语序列到序列语音识别中建模单元与Transformer的比较

A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)

Shiyu Zhou, Linhao Dong, Shuang Xu, Bo Xu

摘要:

建模单元的选择对于自动语音识别(ASR)任务至关重要。传统的ASR系统通常选择上下文相关的状态(CD-状态)或上下文相关的音素(CD-音素)作为其建模单元。然而,它受到了基于序列到序列注意力模型的挑战,该模型将声学,发音和语言模型集成到单个神经网络中。在英语ASR任务中,先前的尝试已经表明,通过基于序列到序列注意力的模型,字素的建模单元可以优于音素的建模单元。在本文中,我们关注的是使用基于序列到序列注意力的模型与Transformer的汉语普通话ASR任务的建模单位。五个建模单位,包括上下文无关的音素(CI音素),音节,单词,子词和字符。在HKUST数据集上的实验表明,无词典建模单元在字符错误率(CER)方面优于词典相关建模单元。在五个建模单元中,基于字符的模型表现最好,并且在HKUST数据集上建立了一个新的最先进的$26.64\%$ CER,而无需手工设计的词典和额外的语言模型集成,这对应于$4.8\%$相对于现有的最佳CER的$28.0\%$的相对改进。

英文摘要:

The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units. However, it has been challenged by sequence-to-sequence attention-based models, which integrate an acoustic, pronunciation and language model into a single neural network. On English ASR tasks, previous attempts have already shown that the modeling unit of graphemes can outperform that of phonemes by sequence-to-sequence attention-based model. In this paper, we are concerned with modeling units on Mandarin Chinese ASR tasks using sequence-to-sequence attention-based models with the Transformer. Five modeling units are explored including context-independent phonemes (CI-phonemes), syllables, words, sub-words and characters. Experiments on HKUST datasets demonstrate that the lexicon free modeling units can outperform lexicon related modeling units in terms of character error rate (CER). Among five modeling units, character based model performs best and establishes a new state-of-the-art CER of $26.64\%$ on HKUST datasets without a hand-designed lexicon and an extra language model integration, which corresponds to a $4.8\%$ relative improvement over the existing best CER of $28.0\%$ by the joint CTC-attention based encoder-decoder network.

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。

↑