Small white version
When I was in middle school, I participated in the recitation competition. The teacher taught me to “mark” in the text, and marked all the pauses, accents, light voices, and rhythm of the speech in the text, so that reading again is very simple.
Speech synthesisTTSThe process is actually a process of reading aloud. If the machine wants to realize the anthropomorphic reading pronunciation, it can actually mark the text in advance, using the Speech Synthetic Markup Language (SSML).
In addition to marking the reading skills, SSML can also mark ambiguous text to determine the reading, for example:
When expressed in time, it can be read as:
- "11:24 pm"
When the score is expressed, it reads as:
- "Twenty-three than twenty-four"
If you need to add BGM in a specific environment in a specific environment, you can also implement a customized TTS through SSML.
Baidu Encyclopedia version
Speech Synthesis Markup Language (SSML), part of W3C's voice interface framework, is a set of specifications for voice applications and building voice applications on the World Wide Web. With SSML, people can use mobile phones more. , desktop computers and other devices to listen to synthesized speech, extending computing and information to every corner of the globe.
SSML is another confusing part of building a VUI based on voice browser technology. SSML can drive the development of portability through a speech synthesis engine interface that is provided by different vendors in a uniform manner. SSML is another W3C standard based on JSML (JSpeech Synthesis Markup Language). SSML is easier to understand based on the problem it is trying to solve.
Speech Synthesis Markup Language (SSML) is an XML-based markup language used in speech synthesis applications.This is a working group that recommends W3C voice browsers. SSML is usually embedded in VoiceXML scripts to drive interactive telephone systems.However, it can also be used alone, for example to create audiobooks.For desktop applications, other markup languages are popular, including Apple's embedded voice commands and Microsoft's SAPI Text to Speech (TTS) markup, which is also an XML language.