Result Image
Instructions:
After selecting the upload file, click Start Testing and the results will be displayed after processing.
Note:

Before experiencing the Yousonic Speech Transmission Index (STI) Blind Estimation Technology, please prepare a vocal recording on site according to the following requirements:

  1. General Requirements: The Yousonic Speech Transmission Index (STI) Blind Estimation Technology only requires a clear recording from within the room to be tested (the recording should consist of continuous speech by a single speaker). Upload the recording to our link to quickly receive the STI value detection experience.
  2. Recording Equipment: Please use devices such as a smartphone, voice recorder, or tablet. Before recording, make sure to turn off any noise reduction features on the device (if it has this function). We recommend using the "wav" format for the recording and setting the sampling rate to no less than 16 kHz.
  3. Recording Environment Setup: In the actual environment to be tested, maintain the actual usage state. Determine the speech transmission path to be tested (i.e., select the speech source and receiving positions). Place the speaker (the person producing the speech) at the speech source position and place the recording device at the selected receiving position.
  4. Preparation of Recording Content: Please prepare the content for the speech in advance. We recommend news reports, literary works, etc., to avoid long periods of silence during the recording. The language, accent, and gender of the speaker are not restricted. The recording should consist of speech from a single speaker at the designated speech source location, recorded by the device placed at the receiving position. (Only the designated speaker should speak during the recording; no other sounds should be made by others, though different recording files can be created by different speakers.)
  5. Recording Process: The speaker should begin reading the prepared content at a normal, clear volume (maintaining a sound pressure level of 60-65 dBA at one meter from the speaker's mouth). The recorder should press the "Record" button on the device, starting the recording at the receiving position. The recording should last between 10 seconds and 2 minutes. Once finished, press the stop button and save the recording. The speaker and recorder can then move to the next speech transmission path (i.e., a new speech source and receiving position) to repeat the process. After all recordings are prepared, you can proceed to the upload step.