具有語言偏差的感測器，用於端到端普通話-英語語碼轉換語音識別（CS SD）

• 2020 年 3 月 17 日
• 筆記

近年來，語言識別資訊被用於提高端到端碼轉換語音識別的性能。然而，以往的工作都是使用額外的語言識別(LID)模型作為輔助模組，這導致了系統的複雜性。在這項工作中，我們提出了一個改進的帶有語言偏差的遞歸神經網路感測器(RNN-T)模型來緩解這個問題。我們使用語言身份來偏見模型來預測CS點。這促進了該模型直接從轉錄中學習語言身份資訊，不需要額外的LID模型。在漢英語料庫SEAME上對該方法進行了評價。與我們的RNN-T基準線相比，該方法可以在兩個測試集上分別實現16.2%和12.9%的相對誤差降低。

原文題目：Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition

原文：Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition. However, previous works use an additional language identification (LID) model as an auxiliary module, which causes the system complex. In this work, we propose an improved recurrent neural network transducer (RNN-T) model with language bias to alleviate the problem. We use the language identities to bias the model to predict the CS points. This promotes the model to learn the language identity information directly from transcription, and no additional LID model is needed. We evaluate the approach on a Mandarin-English CS corpus SEAME. Compared to our RNN-T baseline, the proposed method can achieve 16.2% and 12.9% relative error reduction on two test sets, respectively.

原文作者：Shuai Zhang, Jiangyan Yi, Zhengkun Tian, Jianhua Tao, Ye Bai 原文地址：http://cn.arxiv.org/abs/2002.08126