- 浏览: 1481551 次
- 性别:
- 来自: 南京
文章分类
- 全部博客 (419)
- XMPP (19)
- Android (180)
- Java (59)
- Network (4)
- HTML5 (13)
- Eclipse (9)
- SCM (23)
- C/C++ (4)
- UML (4)
- Libjingle (15)
- Tools&Softwares (29)
- Linphone (5)
- Linux&UNIX (6)
- Windows (18)
- Google (10)
- MISC (3)
- SIP (6)
- SQLite (5)
- Security (4)
- Opensource (29)
- Online (2)
- 文章 (3)
- MemoryLeak (10)
- Decompile (5)
- Ruby (1)
- Image (1)
- Bat (4)
- TTS&ASR (28)
- Multimedia (1)
- iOS (20)
- Asciiflow - ASCII Flow Diagram Tool.htm (1)
- Networking (1)
- DLNA&UPnP (2)
- Chrome (2)
- CI (1)
- SmartHome (0)
- CloudComputing (1)
- NodeJS (3)
- MachineLearning (2)
最新评论
-
bzhao:
点赞123!
Windows的adb shell中使用vi不乱码方法及AdbPutty -
wahahachuang8:
我觉得这种东西自己开发太麻烦了,就别自己捣鼓了,找个第三方,方 ...
HTML5 WebSocket 技术介绍 -
obehavior:
view.setOnTouchListenerview是什么
[转]android 一直在最前面的浮动窗口效果 -
wutenghua:
[转]android 一直在最前面的浮动窗口效果 -
zee3.lin:
Sorry~~
When I build "call ...
Step by Step about How to Build libjingle 0.4
Speech Kit Basics
The Speech Kit framework allows you to add voice recognition and text-to-speech services to your applications easily and quickly. This framework provides access to speech processing components hosted on a server through a clean asynchronous network service API, minimizing overhead and resource consumption. The Speech Kit framework lets you provide fast voice search, dictation, and high-quality, multilingual text-to-speech functionality in your application.
Speech Kit Architecture
The Speech Kit framework is a full-featured, high-level framework that automatically manages all the required low-level services.
At the application level, there are two main components available to the developer: the recognizer and the text-to-speech synthesizer.
In the framework there are several coordinated processes:
- The framework fully manages the audio system for recording and playback.
- The networking component manages the connection to the server and, at the start of a new request, automatically re-establishes connections that have timed-out.
- The end-of-speech detector determines when the user has stopped speaking and automatically stops recording.
- The encoding component compresses and decompresses the streaming audio to reduce bandwidth requirements and decrease latency.
The server system is responsible for the majority of the work in the speech processing cycle. The complete recognition or synthesis procedure is performed on the server, consuming or producing the streaming audio. In addition, the server manages authentication as configured through the developer portal.
Using Speech Kit
You can use the Speech Kit framework in the same way that you use any of the standard iPhone frameworks such as Foundation or UIKit. The only difference is that the Speech Kit framework is a static framework and is entirely contained in your compiled application. This does not affect you as a developer except that you must be certain that you and any other developers working on your application all use the same release of Speech Kit. You can easily ensure this by including the entire framework in your application and your source control.
The Speech Kit framework depends on some core iPhone OS frameworks that you must include as dependencies in your application so that they are available at run time. In addition to Foundation, you must add the System Configuration and Audio Toolbox frameworks to your Xcode project, as follows:
- Start by selecting the Frameworks group within your project.
- Then right-click or command-click Frameworks and, from the menu, select Add ‣ Existing frameworks... .
- Finally, select the required frameworks and click Add . The frameworks appear in the Frameworks folder (see figure below).
To start using the SpeechKit framework, add it to your new or existing project, as follows:
- Open your project and select the group where you want the Speech Kit framework to be stored, for example:file:Frameworks .
- From the menu select Project ‣ Add to Project....
- Then find the framework SpeechKit.framework where you extracted the Dragon Mobile SDK and select Add .
- To ensure that the Speech Kit framework is stored in your project and is not referencing the location where you found it, select Copy items... and then select Add .
- You should now see the Speech Kit framework in your project, which you can expand to view the public headers.
The Speech Kit framework provides one top-level header, which provides access to the complete API including classes and constants. You should import the Speech Kit header in all source files where you intend to use Speech Kit services:
#import <SpeechKit/SpeechKit.h>
You are now ready to start using recognition and text-to-speech services.
Speech Kit Errors
While using the Speech Kit framework, you will occasionally encounter errors. In this framework there is a custom NSError domain, SKSpeechErrorDomain , which includes special error codes and messages to support your development and use. In all cases, errors have a valid localized description set, which may prove useful in development and, in some cases, may be presented to the user.
There are effectively two types of errors that can be expected in this framework.
- The first type are service connection errors and include the SKServerConnectionError and SKServerRetryError codes. These errors indicate that there is some kind of failure in the connection with the speech server. The failure may be temporary, and it can be solved by retrying the query. The error may be the result of an authorization failure or some other network problem.
- The second type are speech processing errors and include the SKRecognizerError and SKVocalizerError codes. These errors indicate a problem with the speech request, ranging from a text format issue to an audio detection failure.
It is essential to always monitor for errors, as signal conditions may generate errors even in a correctly implemented application. The application’s user interface needs to respond appropriately and elegantly to ensure a robust user experience.
发表评论
-
Voice detection for Android
2012-07-23 11:39 2293Here it is, my fist JAVA applic ... -
Google hired one of Nuance soft engineers to help work around all Nuance patents
2012-07-10 14:33 1046很有趣的消息: http://forums.macrumor ... -
The Voice Browser Working Group
2012-07-04 14:38 1936http://www.w3.org/Voice/ ... -
Nuance网站
2012-07-04 14:19 1255http://www.nuance.com/ http: ... -
Nuance HTTP Services
2012-07-03 13:57 943http://dragonmobile.nuancemobil ... -
Nuance - Dragon Mobile SDK - Speech Kit Library Guide (for Android)
2012-07-03 13:09 6473Speech Kit Library Gu ... -
Nuance’s Dragon ID Lets You Unlock Your Smartphone Or Tablet By Talking To It
2012-07-02 11:22 1101http://techcrunch.com/2012/06/0 ... -
Android 4.1 Jelly Bean adds Offline Voice Typing
2012-06-28 14:38 1370Google has added offline vo ... -
iOS的开源库和开源项目
2012-06-14 10:54 982http://www.cocoachina.com/iphon ... -
[iOS开发教程-5]Create Indexed UITableView
2012-06-13 16:31 1705http://www.iphonedevcentral.com ... -
[iOS开发教程-4]Create a UITabBarController from scratch
2012-06-13 15:20 1387http://www.iphonedevcentral.com ... -
[iOS开发教程-3]Create a Detail View Page using UIImageView, UITextView and UILabel
2012-06-13 14:11 2089http://www.iphonedevcentral.com ... -
[iOS开发教程-2]Customize that UIViewCell – Part 1: Using Interface Builder
2012-06-13 13:00 1434http://www.iphonedevcentral.com ... -
[iOS开发教程-1]Hello UITableView!
2012-06-13 11:12 2025http://www.iphonedevcentral.com ... -
Window 7主机与VMware中Mac虚拟机共享文件夹
2012-06-08 23:28 190981. 确保针对Mac虚拟机的VMware Tools的安装 ... -
VMware 8.02虚拟机安装MAC lion 10.7.3教程 附送原版提取镜像InstallESD.iso!
2012-06-08 23:14 6328http://www.winthink.net/thread- ... -
[iOS]深入浅出 iOS 之多线程 NSThread
2012-06-08 15:30 21243http://www.cocoachina.com/bbs/r ... -
Object-C中的Selector概念
2012-06-08 15:25 1051selector可以叫做选择器,其实指的就是对象的方法,也 ... -
CodeBlocks集成Objective-C
2012-06-05 23:35 1158http://www.jxva.com/?act=blog!a ... -
用ultraEdit打造自己的Objective-C IDE for Windows
2012-06-05 21:41 1452http://blog.csdn.net/tomatofly/ ...
相关推荐
cognos案列~Nuance-Watson (HK) Limited
粤语语言包非常难找,这里补充一个资源,粤语NextUp-Nuance-Scansoft-TTS-Chinese-Cantonese-F-Sin-Ji.exe.baiduyun 把后缀扩展名删除 粤语NextUp-Nuance-Scansoft-TTS-Chinese-Cantonese-F-Sin-Ji.exe, 然后解压后...
粤语语言包非常难找,这里补充一个资源,粤语NextUp-Nuance-Scansoft-TTS-Chinese-Cantonese-F-Sin-Ji.exe.baiduyun 把后缀扩展名删除 粤语NextUp-Nuance-Scansoft-TTS-Chinese-Cantonese-F-Sin-Ji.exe, 然后解压后...
潜力无限粤港澳大湾区城市群京东--201809.pdf
TTS-dotdot(科大企业版音库批量转换程序).rarTTS-dotdot(科大企业版音库批量转换程序).rarTTS-dotdot(科大企业版音库批量转换程序).rar
语音生成软件,可以读取更多的文字。
本软件小巧精悍,能够将文本转换为语音,并保存为音频文件。 欢迎下载使用,欢迎Bug反馈。
语音识别技术,Automatic Speech Recognition,简称ASR,是一种让机器听懂人类语言的技术。语言是人类进行信息交流的最主要、最长用、最直接的方式。语音识别技术是实现人机对话的一项重大突破,在国外近年来发展...
Nuance Omnipage SDK v19 帮助文档 OCR 效果还可以的
语音识别技术,Automatic Speech Recognition,简称ASR,是一种让机器听懂人类语言的技术。语言是人类进行信息交流的最主要、最长用、最直接的方式。
公司项目-语音识别率DEMO脚本,nuance平台
nuance uapi介绍及示例,android系统自带的语音开发采用的便是nuance的语音库
利用Nuance语音引擎的语音识别测试程序
Mobile Mobile Mobile Mobile Operators Operators Operators Operators 移动运营商类 China Mobile Communications Corporation 中国移动通信 KDDI CORPORATION 日本 KDDI 电信 NTT DoCoMo, Inc. 日本多科莫电信 ...
[Nuance.PDF阅读器].NuancePDFReader_English
计算机:微软宣布收购Nuance,重新定义AI语音龙头价值.pdf
语言:Deutsch,English,Français,Nederlands,español,italiano 适用于Chrome的Dragon Web Extension 对于Dragon 13或更高版本,此扩展程序可提供...有关详细信息,请参阅Dragon's Help菜单和www.nuance.com/dragon。
光学OCR字元辨识软件。版本17.1。这个版本比以前的版本好用些。识别率不错。