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 1911.04571cs.CLcs.SDeess.AS
收藏

用于语音识别的长跨度语言建模

Long-span language modeling for speech recognition

Microsoft(微软)

Sarangarajan Parthasarathy, William Gale, Xie Chen, George Polovets, Shuangyu Chang

摘要:

我们探索神经语言建模的语音识别的上下文跨越多个句子。我们没有使用单词缓存或文档级特征对当前句子之外的历史进行编码,而是将研究重点放在LSTM和Transformer语言模型隐式学习跨句子边界携带上下文的能力上。我们引入了一种新的架构,将注意力机制纳入LSTM,以结合递归和注意力架构的优点。我们进行语言建模和语音识别实验上公开可用的LibriSpeech语料库。我们表明,传统的训练段落级语料库的结果显着减少困惑相比,训练的一个段落级语料库。我们还描述了语音识别实验,使用长跨度的语言模型在第二遍重新排名,并提供见解的能力,这样的模型,以利用上下文超出当前的句子。

英文摘要:

We explore neural language modeling for speech recognition where the context spans multiple sentences. Rather than encode history beyond the current sentence using a cache of words or document-level features, we focus our study on the ability of LSTM and Transformer language models to implicitly learn to carry over context across sentence boundaries. We introduce a new architecture that incorporates an attention mechanism into LSTM to combine the benefits of recurrent and attention architectures. We conduct language modeling and speech recognition experiments on the publicly available LibriSpeech corpus. We show that conventional training on a paragraph-level corpus results in significant reductions in perplexity compared to training on a sentence-level corpus. We also describe speech recognition experiments using long-span language models in second-pass re-ranking, and provide insights into the ability of such models to take advantage of context beyond the current sentence.

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。

↑