• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Acoustics, Speech and Signal Processing >Improving the Performance of Transformer Based Low Resource Speech Recognition for Indian Languages
【24h】

Improving the Performance of Transformer Based Low Resource Speech Recognition for Indian Languages

机译：提高基于变压器的印度语言低资源语音识别性能

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The recent success of the Transformer based sequence-to-sequence framework for various Natural Language Processing tasks has motivated its application to Automatic Speech Recognition. In this work, we explore the application of Transformers on low resource Indian languages in a multilingual framework. We explore various methods to incorporate language information into a multilingual Transformer, i.e., (i) at the decoder, (ii) at the encoder. These methods include using language identity tokens or providing language information to the acoustic vectors. Language information to the acoustic vectors can be given in the form of one hot vector or by learning a language embedding. From our experiments, we observed that providing language identity always improved performance. The language embedding learned from our proposed approach, when added to the acoustic feature vector, gave the best result. The proposed approach with retraining gave 6% - 11% relative improvements in character error rates over the monolingual baseline.
机译：基于Transformer的序列到序列框架在各种自然语言处理任务中的最新成功激发了其在自动语音识别中的应用。在这项工作中，我们探索了多语言框架中低资源印度语言上的《变形金刚》的应用。我们探索了将语言信息合并到多语言Transformer中的各种方法，即（i）在解码器处，（ii）在编码器处。这些方法包括使用语言身份标记或将语言信息提供给声学矢量。可以以一个热矢量的形式或通过学习语言嵌入的方式来给出针对声学矢量的语言信息。从我们的实验中，我们观察到提供语言身份始终可以提高性能。从我们提出的方法中学习到的语言嵌入，当添加到声学特征向量中时，可以得到最好的结果。所提出的再培训方法在单语基线上的字符错误率相对提高了6％-11％。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号