Speech Interaction Service
Speech Interaction Service
- what's new
- Service Overview
- Getting Started
- SDK Reference
- API Reference
-
FAQs
- General Consulting
- Billing
-
API
- Why Is the Recognition Result Very Poor?
- How Do I Call the APIs of SIS?
- Why Does the Returned Status is Normal But the Recognition Result is Empty?
- What Are the Username, Domain Name, and Project Name in the Token Message Body?
- Can I Call SIS APIs Concurrently?
- What Do I Do If the Error Message "auth failed" Is Displayed During SIS API Calling?
- What Do I Do If SIS API Calling Times Out?
- What Do I Do If the Error Message "The silence time is too long, and the audio will not be recognized" Is Displayed?
- How Do I Obtain a Token?
- SDK
- Error Code
- Deployment
- Regions and AZs
- Permissions
- General Reference
Copied.
Why Is the Recognition Result Very Poor?
Symptom
The recognition result obtained after calling the ASR API is of great difference from the actual result, or the server reports an audio format error.
Solution
- Check whether the audio sampling rate meets the requirements.
You can use tools such as the toolsoft Audio player to listen to a raw audio file and adjust the sampling rate. When the audio file can be played properly, the sampling rate can be used.
- Check whether the sampling rate part in the value of parameter property is the same as the actual sampling rate. For example, in chinese_8k_common, 8k is the sampling rate.
Parent topic: API
Feedback
Was this page helpful?
Provide feedbackThank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.
The system is busy. Please try again later.
For any further questions, feel free to contact us through the chatbot.
Chatbot