Abrupt start to audio

[uselessgames]

respeacker 2 mic

there is an abrupt start to the audio followed by no sound.

I have tried different filters on alsa and ladspa with no success.

This is causing problems in the AI.

How to fix?

[github-actions[bot]]

Stale issue message

[ghost]

@uselessgames , This action was performed automatically. Please describe the issue according to bug template - if the issue was resolved, ignore this message. The issue will be marked as closed in 7 days if inactive.

Describe the bug A clear and concise description of what the bug is.

To Reproduce Steps to reproduce the behavior:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

Expected behavior A clear and concise description of what you expected to happen.

Platform What platform are you running the code on.

• Device: [e.g. Raspberry Pi 4]
• OS: [e.g. Raspbian OS 32bit kernel version ...]
• Version/commit number [e.g. d1816f5]

Relevant log output Please copy and paste any relevant log output.

[AIWintermuteAI]

Hello, @uselessgames !

I am able to reproduce the problem you described with the following setup: Raspberry Pi 4 1 Gb 5.10.17-v7l+ kernel https://github.com/respeaker/seeed-voicecard/commit/b595b95b2184f52e752256cca17e9b92e1a19cd7

Here is three samples I recorded with 2-mic hat - I was speaking before I started recording and I can see a strange upward curve on 0 - 0.1~0.2 segment of the recording.

I'll keep the issue opened and mark it as a known bug. For sound recognition applications, as workaround, the following can be suggested:

• if you do keyword recognition, record audio continuously, then you won't get abrupt start of the audio
• if you do speech recognition, you can omit first ~0.1-0.2 seconds of the audio programmatically so they wouldn't influence the recognition quality. Most of current Deep Leaning algorithms should be able to handle slight noise correctly though and just ouput "silence".