Description: 用于语音识别，基于HMM模型，用C++语言编写。可用连续语音识别-It is based on HMM Model and developed with C++ which could be used to continuous speech recognition. Platform: |
Size: 1538942 |
Author:吴昊 |
Hits:
Description: 用于语音识别，基于HMM模型，用C++语言编写。可用连续语音识别-It is based on HMM Model and developed with C++ which could be used to continuous speech recognition. Platform: |
Size: 1539072 |
Author:吴昊 |
Hits:
Description: 基于CHMM的高性能连续数字语音识别算法.rar-CHMM based on the number of high-performance continuous speech recognition algorithm. Rar Platform: |
Size: 168960 |
Author:dddd |
Hits:
Description: HMM非特定人连续语音识别的嵌入式实现，计算时间基线系统的100％降低到27.91％，识别率仅从基线系统的89.65％下降到89.41％-Non-specific person HMM Continuous Speech Recognition realize embedded computing time baseline system to 100 to 27.91 recognition rate from 89.65 percent of the baseline system dropped to 89.41 Platform: |
Size: 488448 |
Author:王功臣 |
Hits:
Description: 本文介绍了用HMM嵌入训练方法建立连续语音的声学模型-In this paper, HMM embedded training methods used to establish continuous speech acoustic model Platform: |
Size: 304128 |
Author:杨絮 |
Hits:
Description: 基于隐而马可夫的连续语音识别中声学模型的建立及其实现-Based on Hidden Markov and continuous speech recognition acoustic model and its realization Platform: |
Size: 2371584 |
Author:王岐学 |
Hits:
Description: 主要描述了HMM的基本思想及原理，还有其在连续语音中的应用-Main HMM describes the basic idea and principle, as well as its application in continuous speech Platform: |
Size: 173056 |
Author:liujianfei |
Hits:
Description: 语音识别技术的最终目标是要让计算机能与人自由交谈。目前，连续语音识别技术正趋于成熟，语音识别也延伸出了诸多实用化的研究方向。今后，语音识别的重点将集中在自然话语识别与理解、实时语音识别和语音识别鲁棒性等方面。作为一门交叉学科，语音识别所涉及到的技术有信号处理、模式识别、概率论和信息论、发声机理、听觉机理和人工智能等。-The ultimate goal of speech recognition technology is to make computers and allowing others to speak freely. At present, continuous speech recognition technology is maturing, voice recognition is also extended out a lot of practical research directions. In the future, speech recognition will focus on Spontaneous Speech Recognition and Understanding, real-time speech recognition and speech recognition robustness and so on. As an interdisciplinary subject, speech recognition technology involved in a signal processing, pattern recognition, probability theory and information theory, vocal mechanism, hearing mechanism and artificial intelligence. Platform: |
Size: 5483520 |
Author:吴斌 |
Hits:
Description: This first part of the book attempts to provide this information. In this chapter, the basic ideas
of HMMs and their use in speech recognition are introduced. The following chapter then presents a
brief overview of HTK and, for users of older versions, it highlights the main differences in version
2.0 and later. Finally in this tutorial part of the book, chapter 3 describes how a HMM-based
speech recogniser can be built using HTK. It does this by describing the construction of a simple
small vocabulary continuous speech recogniser.-This first part of the book attempts to provide this information. In this chapter, the basic ideas of HMMs and their use in speech recognition are introduced. The following chapter then presents a brief overview of HTK and, for users of older versions, it highlights the main differences in version 2.0 and later. Finally in this tutorial part of the book, chapter 3 describes how a HMM-based speech recogniser can be built using HTK. It does this by describing the construction of a simple small vocabulary continuous speech recogniser. Platform: |
Size: 1805312 |
Author:static |
Hits:
Description: Julius 是一种高性能，两通大词汇量连续语音识别（LVCSR）语音相关的研究和开发的解码器软件。基于字的N-gram和上下文相关的HMM模型，它可以进行几乎实时实时解码目前大多数电脑在60K字听写任务。完全纳入，如树的N-gram词汇，保，跨词的上下文依赖处理，包围梁搜索，高斯修剪，高斯的选择，除了搜索效率等各大搜索技术，它也是模块化小心从模型结构独立，如共享状态triphones的和并列混合模型与任意数量的混合物，州或手机，支持各种HMM的类型。采用标准格式，以配合HTK的，债务工具中央结算系统-CAM可持续土地管理工具包，等其他诸如免费建模工具包- Julius is a high-performance, two-pass large vocabulary continuous speech recognition (LVCSR) decoder software for speech-related researchers and developers. Based on word N-gram and context-dependent HMM, it can perform almost real-time decoding on most current PCs in 60k word dictation task. Major search techniques are fully incorporated such as tree lexicon, N-gram factoring, cross-word context dependency handling, enveloped beam search, Gaussian pruning, Gaussian selection, etc. Besides search efficiency, it is also modularized carefully to be independent from model structures, and various HMM types are supported such as shared-state triphones and tied-mixture models, with any number of mixtures, states, or phones. Standard formats are adopted to cope with other free modeling toolkit such as HTK, CMU-Cam SLM toolkit, etc. Platform: |
Size: 1761280 |
Author:张文原 |
Hits:
Search - Continuous speech hmm