micro_speech example not detecting YES/NO on esp32-s3 Zero (TFMIC-44) #101
Description
Checklist
- Checked the issue tracker for similar issues to ensure this is not a duplicate
- Read the documentation to confirm the issue is not addressed there and your configuration is set correctly
- Tested with the latest version to ensure the issue hasn't been fixed
How often does this bug occurs?
always
Expected behavior
I expected it to detect "Yes" or "No" when I spoke into the i2s mic
Actual behavior (suspected bug)
It kept it printing out: Detected unknown even when there was no sound.
Error logs or terminal output
I (26) boot: ESP-IDF v5.3.1 2nd stage bootloader
I (27) boot: compile time Nov 29 2024 21:32:40
I (27) boot: Multicore bootloader
I (30) boot: chip revision: v0.2
I (34) qio_mode: Enabling default flash chip QIO
I (39) boot.esp32s3: Boot SPI Speed : 80MHz
I (44) boot.esp32s3: SPI Mode : QIO
I (48) boot.esp32s3: SPI Flash Size : 2MB
I (53) boot: Enabling RNG early entropy source...
I (58) boot: Partition Table:
I (62) boot: ## Label Usage Type ST Offset Length
I (69) boot: 0 nvs WiFi data 01 02 00009000 00006000
I (77) boot: 1 phy_init RF data 01 01 0000f000 00001000
I (84) boot: 2 factory factory app 00 00 00010000 00100000
I (92) boot: End of partition table
I (96) esp_image: segment 0: paddr=00010020 vaddr=3c050020 size=16bd0h ( 93136) map
I (118) esp_image: segment 1: paddr=00026bf8 vaddr=3fc91b00 size=02934h ( 10548) load
I (121) esp_image: segment 2: paddr=00029534 vaddr=40374000 size=06ae4h ( 27364) load
I (130) esp_image: segment 3: paddr=00030020 vaddr=42000020 size=440fch (278780) map
I (175) esp_image: segment 4: paddr=00074124 vaddr=4037aae4 size=06fc8h ( 28616) load
I (186) boot: Loaded app from partition at offset 0x10000
I (187) boot: Disabling RNG early entropy source...
I (199) cpu_start: Multicore app
I (208) cpu_start: Pro cpu start user code
I (208) cpu_start: cpu freq: 160000000 Hz
I (208) app_init: Application information:
I (211) app_init: Project name: micro_speech
I (216) app_init: App version: 1
I (220) app_init: Compile time: Nov 29 2024 21:31:12
I (226) app_init: ELF file SHA256: 5fb3635e6...
I (232) app_init: ESP-IDF: v5.3.1
I (236) efuse_init: Min chip rev: v0.0
I (241) efuse_init: Max chip rev: v0.99
I (246) efuse_init: Chip rev: v0.2
I (251) heap_init: Initializing. RAM available for dynamic allocation:
I (258) heap_init: At 3FCAAAF8 len 0003EC18 (251 KiB): RAM
I (264) heap_init: At 3FCE9710 len 00005724 (21 KiB): RAM
I (270) heap_init: At 3FCF0000 len 00008000 (32 KiB): DRAM
I (277) heap_init: At 600FE100 len 00001EE8 (7 KiB): RTCRAM
I (284) spi_flash: detected chip: generic
I (288) spi_flash: flash io: qio
W (291) spi_flash: Detected size(4096k) larger than the size in the binary image header(2048k). Using the size in the binary image header.
W (305) i2s(legacy): legacy i2s driver is deprecated, please migrate to use driver/i2s_std.h, driver/i2s_pdm.h or driver/i2s_tdm.h
I (317) sleep: Configure to isolate all GPIO pins in sleep state
I (324) sleep: Enable automatic switching of GPIO sleep configuration
I (331) main_task: Started on CPU0
I (341) main_task: Calling app_main()
I (361) feature_provider: InitializeMicroFeatures successful
I (391) TF_LITE_AUDIO_PROVIDER: Audio Recording started
Detected unknown, score: 0.87
Detected unknown, score: 0.95
Detected unknown, score: 0.88
Detected unknown, score: 0.93
Detected unknown, score: 0.95
Detected unknown, score: 0.90
Detected unknown, score: 0.85
Detected unknown, score: 0.89
Detected unknown, score: 0.96
Detected unknown, score: 0.99Steps to reproduce the behavior
1.Download this example via vs-code esp-idf extension component menu
2. change the i2s pin config
3. compile and flash it
Project release version
1.3.2
System architecture
Intel/AMD 64-bit (modern PC, older Mac)
Operating system
Windows
Operating system version
Window 11
Shell
PowerShell
Additional context
I was using the INMP441 Microphone Module and tried to make the example work by changing the i2s pin config in the audio_provider.cc here is what I have changed:
#define I2S_WS 3
#define I2S_SD 1
#define I2S_SCK 2
i2s_pin_config_t pin_config = {
.bck_io_num = I2S_SCK,
.ws_io_num = I2S_WS,
.data_out_num = -1,
.data_in_num = I2S_SD};
but after compiling and flashing it I have a problem like above. at first I though I have wiring problem but after checking with this code from dronebotworkshop, I can confirm the microphone is fine:
// Include I2S driver
#include <driver/i2s.h>
// Connections to INMP441 I2S microphone
#define I2S_WS 3
#define I2S_SD 1
#define I2S_SCK 2
// Use I2S Processor 0
#define I2S_PORT I2S_NUM_0
// Define input buffer length
#define bufferLen 64
int16_t sBuffer[bufferLen];
void i2s_install() {
// Set up I2S Processor configuration
const i2s_config_t i2s_config = {
.mode = i2s_mode_t(I2S_MODE_MASTER | I2S_MODE_RX),
.sample_rate = 44100,
.bits_per_sample = i2s_bits_per_sample_t(16),
.channel_format = I2S_CHANNEL_FMT_ONLY_LEFT,
.communication_format = i2s_comm_format_t(I2S_COMM_FORMAT_STAND_I2S),
.intr_alloc_flags = 0,
.dma_buf_count = 8,
.dma_buf_len = bufferLen,
.use_apll = false
};
i2s_driver_install(I2S_PORT, &i2s_config, 0, NULL);
}
void i2s_setpin() {
// Set I2S pin configuration
const i2s_pin_config_t pin_config = {
.bck_io_num = I2S_SCK,
.ws_io_num = I2S_WS,
.data_out_num = -1,
.data_in_num = I2S_SD
};
i2s_set_pin(I2S_PORT, &pin_config);
}
void setup() {
// Set up Serial Monitor
Serial.begin(115200);
Serial.println(" ");
delay(1000);
// Set up I2S
i2s_install();
i2s_setpin();
i2s_start(I2S_PORT);
delay(500);
}
void loop() {
// False print statements to "lock range" on serial plotter display
// Change rangelimit value to adjust "sensitivity"
int rangelimit = 3000;
Serial.print(rangelimit * -1);
Serial.print(" ");
Serial.print(rangelimit);
Serial.print(" ");
// Get I2S data and place in data buffer
size_t bytesIn = 0;
esp_err_t result = i2s_read(I2S_PORT, &sBuffer, bufferLen, &bytesIn, portMAX_DELAY);
if (result == ESP_OK)
{
// Read I2S data buffer
int16_t samples_read = bytesIn / 8;
if (samples_read > 0) {
float mean = 0;
for (int16_t i = 0; i < samples_read; ++i) {
mean += (sBuffer[i]);
}
// Average the data reading
mean /= samples_read;
// Print to serial plotter
Serial.println(mean);
}
}
}
