Lucca Pirovano
79 lines
3.7 KiB
Markdown
79 lines
3.7 KiB
Markdown
---
|
||
title: "Volume display and audio underrun fixes"
|
||
tags: []
|
||
author: claude
|
||
count: 2
|
||
exporter: 3.1.0
|
||
date: 2026-07-15T19-21-17+0000
|
||
url: https://claude.ai/chat/0c44df5d-e4f0-425d-9730-53563dd8f762
|
||
---
|
||
|
||
# Volume display and audio underrun fixes
|
||
|
||
## Table of Contents
|
||
|
||
- [1: The wav file had distant sounds from my coworkers yapping. I didnt get…](#chat-1)
|
||
- [2: audio works but is too quiet, amplify it and mix it all to make it mon…](#chat-2)
|
||
|
||
## chat-1
|
||
|
||
> The wav file had distant sounds from my coworkers yapping. I didnt get to talk but that proves the mic does do something
|
||
>
|
||
> ┌──(lucka㉿theuniverseismine)-[~/programming/py/naowalk]
|
||
> └─$ python3 naomictest.py --ip spike.local --port 9561
|
||
> [W] 1784142061.737086 18238 qi.path.sdklayout: No Application was created, trying to deduce paths
|
||
> ✅ Connected to spike.local
|
||
>
|
||
> === TEST 1: Mic hardware energy (all 4 mics) ===
|
||
> Make noise near the robot's head (clap, talk right up close to it) for 10s...
|
||
> t=0s front=1.86 rear=1.76 left=22.41 right=25.90
|
||
> t=1s front=1.78 rear=1.66 left=10.84 right=12.57
|
||
> t=2s front=1.77 rear=1.75 left=12.23 right=13.08
|
||
> t=3s front=1.75 rear=1.73 left=18.84 right=19.08
|
||
> t=4s front=1.69 rear=1.78 left=18.88 right=18.45
|
||
> t=5s front=1.73 rear=1.75 left=17.76 right=19.11
|
||
> t=6s front=1.71 rear=1.79 left=15.86 right=14.67
|
||
> t=7s front=1.73 rear=1.84 left=20.97 right=21.05
|
||
> t=8s front=1.83 rear=1.72 left=14.95 right=15.82
|
||
> t=9s front=1.68 rear=1.78 left=10.71 right=12.04
|
||
> ⚠ Flat mic(s): front, rear. The others responded normally, which points to a fault specific to front, rear rather than the audio
|
||
> pipeline as a whole (that pipeline is clearly working for the others).
|
||
>
|
||
> === TEST 2: Local on-robot recording ===
|
||
> Recording 5s directly to /home/nao/mic_test.wav on the robot itself (this bypasses the network stream and your laptop's audio sta
|
||
> ck entirely)...
|
||
> Done. Pull it off and play it with:
|
||
> scp nao@spike.local:/home/nao/mic_test.wav .
|
||
> (then open mic_test.wav in any media player - it's 4-channel, so check all channels)
|
||
> If that file has clearly audible sound, the mic and robot are fine and the
|
||
> bug is specifically in naowalk.py's live-streaming path.
|
||
>
|
||
> === TEST 3: Robot's own speaker ===
|
||
> Press Enter to have the robot say a test phrase out loud...hi
|
||
> If you heard the robot speak just now, its speaker output is fine (this is unrelated to hearing its mic on your laptop, but rules
|
||
> out a robot-wide audio fault).
|
||
>
|
||
> Done. Report back which test(s) failed and we'll know exactly where to look.
|
||
|
||
That's the smoking gun. Look at the pattern: **left and right respond strongly to noise (10–25), front and rear are dead flat (~1.7–1.9)** — every single test agrees. And the recording that had audible coworker chatter makes total sense now: it's a 4-channel file, so the left/right tracks caught that audio while front/rear stayed silent.
|
||
|
||
This was never a bug in the code. `naowalk.py` was explicitly requesting the **front** mic (`setClientPreferences(..., 3, 0)` — channel 3 = FRONTCHANNEL), which happens to be one of the two dead mics on this robot. It was faithfully streaming from a mic that produces no signal.
|
||
|
||
Fix: point the stream at a working mic instead — left or right. Let me make it configurable so you can pick whichever sounds better:
|
||
|
||
Now add the CLI flag and pass it through:
|
||
|
||
Let's verify and ship it:
|
||
|
||
___
|
||
###### [top](#table-of-contents)
|
||
## chat-2
|
||
|
||
> audio works but is too quiet, amplify it and mix it all to make it mono
|
||
|
||
Now let's rewrite `SoundReceiver` to request all mics, mix down to mono skipping dead channels, and apply amplification with a soft limiter:
|
||
|
||
___
|
||
###### [top](#table-of-contents)
|
||
|