Automatic speech recognition: a communication perspective
Automatic speech recognition: a communication perspective
复制标题
自动语音识别：通信视角
DOI：
--
复制
发表时间：
1999
期刊：
影响因子：
--
通讯作者：
B. Atal
中科院分区：
文献类型：
--
作者：
B. Atal
语音识别通常被认为是模式识别领域的问题，其中首先估计待识别的每个模式的概率密度函数，然后使用贝叶斯定理来识别为所观察的语音数据提供最高似然的模式。在本文中，我们采取不同的方法来解决这个问题。在语音识别中，目标是通过语音进行信息通信，我们从通信的角度讨论语音识别的基础知识。在声学水平上的语音信号具有64 kb/s的比特率，但是基本的声音模式具有小于100 B/s的信息率。这种高比特率在声学水平上的作用是什么？我们讨论的原则解码模式是淹没在海洋中的看似无关的信息。
Speech recognition is usually regarded as a problem in the field of pattern recognition, where one first estimates the probability density function of each pattern to be recognized and then uses Bayes theorem to identify the pattern which provides the highest likelihood for the observed speech data. In this paper, we take a different approach to this problem. In speech recognition, the goal is communication of information by voice and we discuss the basics of speech recognition from a communication perspective. The speech signal at the acoustic level has a bit rate of 64 kb/s but the underlying sound patterns have an information rate of less than 100 b/s. What is the role of this high bit rate at the acoustic level? We discuss the principles of decoding patterns that are submerged in an ocean of seemingly irrelevant information.