1 Commits

Author SHA1 Message Date
9a3d026176 feat : Updated src/main.cpp to utilize FormatConverterStream for converting 32-bit I2S input to 16-bit output and configured an AudioFFTBase with the correct bits per sample
- Modified `src/main.cpp` to use `FormatConverterStream` for converting 32-bit I2S input to 16-bit output, then configured an `AudioFFTBase` with the appropriate bits per sample.
2025-04-18 21:48:47 +02:00
2 changed files with 90 additions and 123 deletions

View File

@@ -33,6 +33,4 @@ monitor_filters = esp32_exception_decoder
lib_deps =
https://github.com/pschatzmann/arduino-audio-tools.git
https://github.com/pschatzmann/arduino-audio-driver.git
https://github.com/tzapu/WiFiManager.git
me-no-dev/AsyncTCP
https://github.com/me-no-dev/ESPAsyncWebServer.git

View File

@@ -1,130 +1,99 @@
#include <Arduino.h>
#include <driver/i2s.h>
#include <deque>
#include "AudioTools.h"
// #include "AudioTools/AudioLibs/AudioI2SStream.h"
#include "AudioTools/AudioLibs/AudioRealFFT.h" // or AudioKissFFT
// you shouldn't need to change these settings
#define SAMPLE_BUFFER_SIZE 512
#define SAMPLE_RATE 8000
// most microphones will probably default to left channel but you may need to tie the L/R pin low
#define I2S_MIC_CHANNEL I2S_CHANNEL_FMT_ONLY_LEFT
// either wire your microphone to the same pins or change these to match your wiring
#define I2S_MIC_SERIAL_CLOCK 8
#define I2S_MIC_LEFT_RIGHT_CLOCK 9
#define I2S_MIC_SERIAL_DATA 10
I2SStream i2sStream; // I2S input stream for INMP441
AudioRealFFT fft; // FFT analyzer
FormatConverterStream converter(i2sStream); // Convert 32-bit input to 16-bit output
StreamCopy copier(fft, converter); // copy converted data to FFT
// Add sample history tracking for range limiting
#define HISTORY_DURATION_MS 1000 // 1 seconds history
#define SAMPLES_PER_MS (SAMPLE_RATE / 1000)
#define HISTORY_SIZE (HISTORY_DURATION_MS * SAMPLES_PER_MS)
int channels = 1; // INMP441 is mono
int samples_per_second = 11025;
int input_bits_per_sample = 32; // INMP441 sends 24-bit data in 32-bit words
int fft_bits_per_sample = 16;
#define MAX_RANGE_LIMIT 150000000 // Maximum allowed range limit
#define DEFAULT_RANGE_LIMIT 20000 // Default range limit when no history
AudioInfo from(samples_per_second, channels, input_bits_per_sample);
AudioInfo to(samples_per_second, channels, fft_bits_per_sample);
class AudioLevelTracker {
public:
AudioLevelTracker() {
resetMaxLevel();
}
void updateMaxLevel(int32_t sample) {
uint32_t currentTime = millis();
// Remove old samples (older than 10 seconds)
while (!sampleHistory.empty() &&
(currentTime - sampleHistory.front().timestamp) > HISTORY_DURATION_MS) {
sampleHistory.pop_front();
}
// Add new sample, but cap it at MAX_RANGE_LIMIT
int32_t absValue = abs(sample);
absValue = min(absValue, MAX_RANGE_LIMIT); // Cap the value
SamplePoint newPoint = {currentTime, absValue};
sampleHistory.push_back(newPoint);
// Update maximum
maxLevel = 0;
for (const auto& point : sampleHistory) {
if (point.value > maxLevel) {
maxLevel = point.value;
}
}
}
int32_t getMaxLevel() const {
return maxLevel;
}
void resetMaxLevel() {
maxLevel = 0;
sampleHistory.clear();
}
private:
struct SamplePoint {
uint32_t timestamp;
int32_t value;
const char* solfegeName(uint8_t midiNote) {
static const char* solfegeNames[] = {
"Do", "Do#", "Re", "Re#", "Mi", "Fa", "Fa#", "Sol", "Sol#", "La", "La#", "Si"
};
std::deque<SamplePoint> sampleHistory;
int32_t maxLevel;
};
return solfegeNames[midiNote % 12];
}
AudioLevelTracker audioLevelTracker;
void fftResult(AudioFFTBase &fft) {
float diff;
auto result = fft.result();
// don't mess around with this
i2s_config_t i2s_config = {
.mode = (i2s_mode_t)(I2S_MODE_MASTER | I2S_MODE_RX),
.sample_rate = SAMPLE_RATE,
.bits_per_sample = I2S_BITS_PER_SAMPLE_32BIT,
.channel_format = I2S_CHANNEL_FMT_ONLY_LEFT,
.communication_format = I2S_COMM_FORMAT_STAND_I2S, // Updated from I2S_COMM_FORMAT_I2S
.intr_alloc_flags = ESP_INTR_FLAG_LEVEL1,
.dma_buf_count = 4,
.dma_buf_len = 1024,
.use_apll = false,
.tx_desc_auto_clear = false,
.fixed_mclk = 0};
if (result.magnitude > 100) { // avoid noise floor
float magnitude_dB = 20.0 * log10(result.magnitude);
float freq = result.frequency;
// and don't mess around with this
i2s_pin_config_t i2s_mic_pins = {
.bck_io_num = I2S_MIC_SERIAL_CLOCK,
.ws_io_num = I2S_MIC_LEFT_RIGHT_CLOCK,
.data_out_num = I2S_PIN_NO_CHANGE,
.data_in_num = I2S_MIC_SERIAL_DATA};
// MIDI note number
int midiNote = round(69 + 12.0 * log2(freq / 440.0));
const char* solfege = solfegeName(midiNote);
int octave = (midiNote / 12) - 1;
void setup()
{
// we need serial output for the plotter
Serial.print(freq, 0);
Serial.print(" Hz | ");
Serial.print("MIDI ");
Serial.print(midiNote);
Serial.print(" | ");
Serial.print("Note: ");
Serial.print(result.frequencyAsNote(diff));
Serial.print(" | ");
Serial.print("Solfège: ");
Serial.print(solfege);
Serial.print(octave);
Serial.print(" | dB: ");
Serial.print(magnitude_dB, 2);
Serial.print(" | Diff: ");
Serial.println(diff, 2);
Serial.print(" | Amp: ");
Serial.println(result.magnitude, 0);
}
}
void setup() {
Serial.begin(115200);
// start up the I2S peripheral
i2s_driver_install(I2S_NUM_0, &i2s_config, 0, NULL);
i2s_set_pin(I2S_NUM_0, &i2s_mic_pins);
AudioToolsLogger.begin(Serial, AudioToolsLogLevel::Warning);
// Configure I2SStream for INMP441
auto cfg = i2sStream.defaultConfig(RX_MODE);
cfg.i2s_format = I2S_STD_FORMAT;
cfg.bits_per_sample = input_bits_per_sample;
cfg.channels = channels;
cfg.sample_rate = samples_per_second;
cfg.is_master = true;
cfg.pin_bck = 8; // SCK
cfg.pin_ws = 9; // WS
cfg.pin_data = 10; // SD
i2sStream.begin(cfg);
// Configure FormatConverterStream to convert 32-bit to 16-bit
converter.begin(from, to); // Convert to 16-bit
// Configure FFT
auto tcfg = fft.defaultConfig();
tcfg.length = 8192; // 186ms @ 11kHz minimun C2 theoretical
tcfg.channels = channels;
tcfg.sample_rate = samples_per_second;
tcfg.bits_per_sample = fft_bits_per_sample; // FFT expects 16-bit data after conversion
tcfg.callback = &fftResult;
fft.begin(tcfg);
Serial.println("Setup complete. Listening...");
}
int32_t raw_samples[SAMPLE_BUFFER_SIZE];
void loop()
{
// read from the I2S device
size_t bytes_read = 0;
i2s_read(I2S_NUM_0, raw_samples, sizeof(int32_t) * SAMPLE_BUFFER_SIZE, &bytes_read, portMAX_DELAY);
int samples_read = bytes_read / sizeof(int32_t);
// Calculate dynamic range limit based on max level from last 10 seconds
int32_t currentMaxLevel = audioLevelTracker.getMaxLevel();
int32_t rangelimit = currentMaxLevel > 0 ? currentMaxLevel : DEFAULT_RANGE_LIMIT; // fallback to default if no history
// dump the samples out to the serial channel
for (int i = 0; i < samples_read; i++)
{
// Update the max level tracker with current sample
audioLevelTracker.updateMaxLevel(raw_samples[i]);
// Print range limits for plotter
Serial.print(rangelimit * -1);
Serial.print(" ");
Serial.print(rangelimit);
Serial.print(" ");
// Print the actual sample
Serial.printf("%ld\n", raw_samples[i]);
}
void loop() {
copier.copy(); // Stream mic data into FFT processor
}