首页> 外文期刊>Computer speech and language >Algorithms for data-driven ASR parameter quantization
【24h】

Algorithms for data-driven ASR parameter quantization

机译:数据驱动的ASR参数量化算法

获取原文
获取原文并翻译 | 示例
           

摘要

There is fast growing research on designing energy-efficient computational devices and applications running on them. As one of the most compelling applications for mobile devices, automatic speech recognition (ASR) requires new methods to allow it to use fewer computational and memory resources while still achieving a high level of accuracy. One way to achieve this is through parameter quantization. In this work, we compare a variety of novel sub-vector clustering procedures for ASR system parameter quantization. Specifically, we look at systematic data-driven sub-vector selection techniques, most of which are based on entropy minimization, and others on recognition accuracy maximization on a development set. We compare performance on two speech databases, phonebook, an isolated word speech recognition task, and timit, a phonetically diverse connected-word speech corpus. While the optimal entropy-minimizing or accuracy-driven quantization methods are intractable, several simple schemes including scalar quantization with separate codebooks per parameter and joint scalar quantization with normalization perform well in their attempt to approximate the optimal clustering.
机译:关于设计节能计算设备及其上运行的应用的研究正在迅速增长。作为移动设备最引人注目的应用之一,自动语音识别(ASR)需要新的方法,以使其能够使用较少的计算和内存资源,同时仍能实现较高的准确性。实现此目的的一种方法是通过参数量化。在这项工作中,我们比较了用于ASR系统参数量化的各种新颖的子向量聚类程序。具体来说,我们研究系统的数据驱动子矢量选择技术,其中大多数基于熵最小化,而其他则基于开发集上的识别精度最大化。我们比较两个语音数据库的性能,电话簿是一个孤立的单词语音识别任务,而timit是一个语音多样的连接单词语音语料库。尽管最佳的熵最小化或精度驱动的量化方法很棘手,但是一些简单的方案(包括对每个参数使用单独码本的标量量化和归一化的联合标量量化)在逼近最佳聚类方面表现良好。

著录项

  • 来源
    《Computer speech and language》 |2006年第4期|p. 625-643|共19页
  • 作者单位

    Computer Science and Engineering Department, University of Washington, P.O. Box 352350, Seattle, WA 98195, United States;

    Electrical Engineering Department, University of Washington, Seattle, WA 98195, United States;

    Electrical Engineering Department, University of Washington, Seattle, WA 98195, United States;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 计算技术、计算机技术;
  • 关键词

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