An overview of Microsoft's TTS trial series (thoughts only)

Source: Internet
Author: User

When I write a blog for the first time, I don't know how to get started, and my thoughts are messy. Let's talk about how to enter the garden first. I hope it won't waste too much valuable time >_<.

The relationship with the blog site should be the beginning of the 3rd. At that time, the Office of Academic Affairs wanted to develop an academic Arrangement System. To save money, I was looking for someone from the department. So I took it with the other two students. If you don't talk about money or anything, then you need to understand the requirements, determine the scheme, and assign tasks (the first time you do a whole small project, it's messy ). We learned C # from our sophomore year, So C # and ASP. NET are used for development. At that time, there were two difficult problems for us: first, the system needs to generate the entered content into a Word document in the format specified by the Office of Academic Affairs, the second is to generate multiple structure charts in word based on the input content. One of the students has been working on projects with their teachers and is familiar with C # Word processing. However, considering that using code to directly control the Word Drawing structure is inconvenient and the format is not easy to control, we plan to use Visio to draw a structure chart, and finally export and insert the specified location of word. Therefore, the student finally processes the word based on the given template and is responsible for the layout of the webpage (as far as possible, the Word template is consistent), while another student and I are responsible for studying C # To control the Visio drawing and export. For C # To control the Visio drawing, I didn't know it at the time. So I checked the help document of Visio and asked for help. Then I found outWu huacongThe second-time blog developed by the teacher Visio, So I downloaded the research and extracted the code I needed from it. After modification, I can basically draw a structure diagram in Visio. In addition, I kept trying, finally, the structure chart is dynamically drawn based on the data in the database and the size of the structure box is automatically scaled. That is to say, I found a new world, the blog garden, and began to pay attention to it. I would like to thank Mr. Wu ^_^.

After finishing the process of entering the park, it is time to enter the topic.

Thinking of a TTS program is actually related to your own eyes. My eyes have been getting worse, and I often stare at my computer and cell phone. As a result, I think that since my eyes are always staring at my computer, I can still exercise my ears. The first thought in this mind is to read the text in the computer by a whole program, and the second thought is to see if there is any ready-made available online. After searching, there are some such software on the Internet, such as reading and listening by a lazy person, but the effect is not good and the other resources are hard to find. We also found that the voice Effect of Tencent was great, but of course it was not open-source and only allowed to experience it. Finally, I plan to build a trainer myself. Although it is not clear whether the trainer can be completed or the effect can be achieved, it is worthwhile to try it. Fortunately, Microsoft has its own voice engine that can be directly used in C #, saving a lot of trouble.

The next step is the crazy idea about this program function (custom requirement). Since it is crazy, it will not be able to be implemented, but it should be noted down.

1. First, you must be able to read local files, including word, txt, and PDF files.

2. You can read the content on the webpage. This is very important. You cannot copy and paste the articles on the webpage into word every time. If possible, it is best to read the specified content on the webpage, such as the title and body. Because it may be difficult to directly read the webpage, I plan to enter the URL in the program, and then obtain the content of the webpage for analysis.

3. Because Microsoft's voice engine seems to be able to only recognize text (including Chinese and English, and related to the engine), if the content provided by 1 and 2 is not readable, the system prompts whether the image or link is used (that is, the unreadable content is replaced with the specified prompt information according to the type). In addition, some special tags do not need to be read, this involves analyzing and processing the obtained content.

4. The voice engine does not seem to be particularly accurate in terms of sentence breaking. Although Microsoft's engine can differentiate phrases, the time interval between phrases is too obvious. It sounds like a fault, and if you choose not to read punctuation, some of the content that needs to be read will not be read. In this case, you need to replace the content and display it as text. For example, there are multiple date formats, but they are separated by punctuation marks, the date needs to be converted into Chinese characters.

5. You can take words and read them like youdao dictionary, or move your mouse over some words to read them.

6. You can generate audio files that can be played, such as MP3, to facilitate storage on your mobile phone or for later use.

This is not a good brain, so now I can only think of this, it is also the main function. Since you are currently studying WPF, you plan to use WPF for development. The writing is a bit messy and there is no useful content. The most important thing is that you don't know which type of articles to be written or where to publish them. I hope you don't mind. If you have any comments or suggestions, you may wish to discuss them and study them together.

An overview of Microsoft's TTS trial series (thoughts only)

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.