It is a multi-lingual (97 languages) text content automatic recognition and segmentation tool. 强大的TTS多语言(97种语言)混合文本内容自动分词工具。
It is a multi lingual (97 languages) text content automatic recognition and segmentation tool Powerful TTS multi language (97 languages) hybrid text content automatic segmentation tool. (2024-02-02, Python, 0KB, 下载0次)
“使用VITtransformer进行动物检测，测试精度为97%”项目是一项重点突出、可实现的举措，旨在建立...
The "Animal Detection Using VIT Transformers with 97% Testing Accuracy" project is a focused and achievable initiative aimed at building an accurate animal detection system. Leveraging Vision Transformer (VIT) models, this project is dedicated to the specific goal of achieving a high testing accuracy of 97% in identifying. (2023-11-01, Jupyter Notebook, 0KB, 下载0次)
百度导航支持语音播报(使用语言播报,需要在[http: app.navi.baidu.com ttsregister appinfo导航TTS平台中进行注册申请),路线规划及导航](http: app.navi.baidu.com ttsregister appinfo%E5%AF%BC%E8%88%AATTS%E5%B9%B3%E5%8F%B0%E4%B8%AD%E8%BF%9B%E8%A1%8C%E6%B3%A8%E5%86%8C%E7%94%B3%E8%AF%B7%EF%BC%89%EF%BC%8C%E8%B7%AF%E7%BA%BF%E8%A7%84%E5%88%92%E5%8F%8A%E5%AF%BC%E8%88%AA)
Baidu Navigation supports voice broadcasting (using language broadcasting, registration application is required on the TTS platform for navigation), route planning and navigation (http: app. navi. baidu. com ttsregister appinfo% E5% AF% BC% E8% 88% AATTS% E5% B9% B3% E5% 8F% B0% E4% B8% AD% E8% BF% 9B% E8% A1% 8C% E6% B3% A8% E5% 86% 8C% E7% 94% B3% E8% AF% B8% 7% EF% BC% 89% EF% BC% 8C% E8% B7% AF% E7% BA% BF% E8% A7% 84% E5% 88% 92% E5% 8F% 8A% E5% AF% BC% E8% 88% AA) (2017-11-02, Java, 10816KB, 下载0次)
DOA algorithm using in microphone array - 6microphones
DOA algorithm using in microphone array - 6microphones (2020-03-10, C++, 795KB, 下载0次)
Beamforming tests can used to test how good is a bf implementation
Beamforming tests can used to test how good is a bf implementation (2011-09-29, matlab, 10KB, 下载7次)
基于动态贝叶斯网络的连续语音识别框架及其Token传递模型
Dynamic Bayesian Network Based Continuous Speech Recognition Framework and its Token transfer model (2011-03-29, C/C++, 669KB, 下载50次)
摘要说话人识别在自动身份鉴别方面具有重要的现实意义。文章在分析了说话人识别实现的可行性基础上*提
出采用长时线性预测倒谱 +,--.,)系数和矢量量化 /0)模型的不依赖于文本的说话人识别方法，并成功地应用于
一个数据库查询系统中。
65DL5<?E5=7?9?AD7?8=CDH H?>=?9?AD=7 D66@?AD7?8=H?=D 78:D7?A?=E?G?E D@<5A8>=?7?8=D<5D#M=7C?H 6D65<*
7C5 68HH?N?@?7I 89 DAA8:6@?HC:5=7 89 H65DL5<?E5=7?9?AD7?8=?H D=D@IO5E*D=E 7C5=D:57C8E 98<75P7Q?=E565=E5=7
H65DL5<?E5=7?9?AD7?8=?H 6<5H5=75E*RC?AC?H NDH5E 8=G5A78<S D=7?7D?8= /0)D=E@8=>Q7?:5+,--.,6D<D:575<H#
(2009-09-23, matlab, 76KB, 下载20次)
Gerven, S. V. & Xie, F. "A Comparative Study of Speech Detection Methods" EUROSPEECH 97, 1997 , 1095-1098.
Gerven, S. V. & Xie, F. "A Comparative Study of Speech Detection Methods" EUROSPEECH 97, 1997 , 1095-1098.
(2009-05-18, matlab, 2KB, 下载4次)
：用C 语言实现了一个用于控制家电开关的声音模块. 该声音模块采用当前语音识别系统的主流技
术——隐马尔可夫模型（HMM）技术，以及线性预测倒谱计算和矢量量化技术. 命令（单词）的正确识别率
在97 以上. 介绍了声音模块的设计方案，并就实现该声音模块的过程中所遇到的具体问题进行了讨论.
: The C language realization of a switch used to control the voice module appliances. The sound module voice recognition systems using current mainstream technologies- Hidden Markov Model (HMM) technology, as well as the linear prediction cepstrum calculation and vector quantization technology. command (word) the correct recognition rate in more than 97 . introduced a sound module design and the realization of the sound module on the course of the specific problems encountered were discussed. (2009-04-27, Visual C++, 196KB, 下载58次)
opnet CS_4700_4s_e6_fr2_sl4_ref
opnet CS_4700_4s_e6_fr2_sl4_ref (2009-04-16, matlab, 22KB, 下载7次)