Sai Yamanoor
Created September 4, 2024

Geocaching Aid for Visually Challenged

A visual aid with a microphone and speech synthesis shield for geocaching

15
Geocaching Aid for Visually Challenged

Things used in this project

Story

Read more

Schematics

System Schematic

Code

Speech Synthesis Code

Arduino
#include <WiFi.h>
#include <NetworkClient.h>
#include <WebServer.h>
#include <ESPmDNS.h>
#include "DFRobot_SpeechSynthesis.h"
#include <HardwareSerial.h>
#include <uri/UriBraces.h>
#include <uri/UriRegex.h>

const char *ssid = "************";
const char *password = "************";

const char* PARAM_INPUT_1 = "input1";

WebServer server(80);
HardwareSerial MySerial0(0);
DFRobot_SpeechSynthesis_UART ss;
const char index_html[] PROGMEM = R"rawliteral(
<!DOCTYPE HTML><html><head>
  <title>ESP Input Form</title>
  <meta name="viewport" content="width=device-width, initial-scale=1">
  <script>
    function submitMessage() {
      alert("Saved value to ESP LittleFS");
      setTimeout(function(){ document.location.reload(false); }, 500);   
    }
  </script></head><body>
  <form action="/get" target="hidden-form">
    inputString: <input type="text" name="inputString">
    <input type="submit" value="Submit" onclick="submitMessage()">
  </form><br>
  <iframe style="display:none" name="hidden-form"></iframe>
</body></html>)rawliteral";

void setup(void) {
  Serial.begin(9600);
  MySerial0.begin(115200, SERIAL_8N1, -1, -1);
  WiFi.mode(WIFI_STA);
  WiFi.begin(ssid, password);
  Serial.println("");

  // Wait for connection
  while (WiFi.status() != WL_CONNECTED) {
    delay(500);
    Serial.print(".");
  }
  Serial.println("");
  Serial.print("Connected to ");
  Serial.println(ssid);
  Serial.print("IP address: ");
  Serial.println(WiFi.localIP());

  if (MDNS.begin("esp32")) {
    Serial.println("MDNS responder started");
  }

  server.on(F("/"), []() {
    server.send(200, "text/html", index_html);
  });

   server.on("/get", HTTP_GET, [] () {
    String inputMessage;
    String inputParam;
    // GET input1 value on <ESP_IP>/get?input1=<inputMessage>
    for (uint8_t i = 0; i < server.args(); i++) {
    inputMessage += " " + server.argName(i) + ": " + server.arg(i) + "\n";
    }
    ss.speak(server.arg(i));
    Serial.println(inputMessage);
    
  });

  server.begin();
  Serial.println("HTTP server started");
  
  ss.begin(MySerial0);
  ss.setVolume(5);
  
  ss.speak(F("Hello, I'm Speech Synthesis module"));
}

void loop(void) {
  server.handleClient();
  delay(2);  //allow the cpu to switch to other tasks
}

Microphone command code

Arduino
// If your target is limited in memory remove this macro to save 10K RAM
#define EIDSP_QUANTIZE_FILTERBANK   0

/*
 ** NOTE: If you run into TFLite arena allocation issue.
 **
 ** This may be due to may dynamic memory fragmentation.
 ** Try defining "-DEI_CLASSIFIER_ALLOCATION_STATIC" in boards.local.txt (create
 ** if it doesn't exist) and copy this file to
 ** `<ARDUINO_CORE_INSTALL_PATH>/arduino/hardware/<mbed_core>/<core_version>/`.
 **
 ** See
 ** (https://support.arduino.cc/hc/en-us/articles/360012076960-Where-are-the-installed-cores-located-)
 ** to find where Arduino installs cores on your machine.
 **
 ** If the problem persists then there's not enough memory for this model and application.
 */

/* Includes ---------------------------------------------------------------- */
#include <tracker_inferencing.h>

#include "freertos/FreeRTOS.h"
#include "freertos/task.h"

#include "driver/i2s.h"

/** Audio buffers, pointers and selectors */
typedef struct {
    signed short *buffers[2];
    unsigned char buf_select;
    unsigned char buf_ready;
    unsigned int buf_count;
    unsigned int n_samples;
} inference_t;

static inference_t inference;
static const uint32_t sample_buffer_size = 2048;
static signed short sampleBuffer[sample_buffer_size];
static bool debug_nn = false; // Set this to true to see e.g. features generated from the raw signal
static int print_results = -(EI_CLASSIFIER_SLICES_PER_MODEL_WINDOW);
static bool record_status = true;

/**
 * @brief      Arduino setup function
 */
void setup()
{
    // put your setup code here, to run once:
    Serial.begin(115200);
    // comment out the below line to cancel the wait for USB connection (needed for native USB)
    while (!Serial);
    Serial.println("Edge Impulse Inferencing Demo");

    // summary of inferencing settings (from model_metadata.h)
    ei_printf("Inferencing settings:\n");
    ei_printf("\tInterval: ");
    ei_printf_float((float)EI_CLASSIFIER_INTERVAL_MS);
    ei_printf(" ms.\n");
    ei_printf("\tFrame size: %d\n", EI_CLASSIFIER_DSP_INPUT_FRAME_SIZE);
    ei_printf("\tSample length: %d ms.\n", EI_CLASSIFIER_RAW_SAMPLE_COUNT / 16);
    ei_printf("\tNo. of classes: %d\n", sizeof(ei_classifier_inferencing_categories) / sizeof(ei_classifier_inferencing_categories[0]));

    run_classifier_init();
    ei_printf("\nStarting continious inference in 2 seconds...\n");
    ei_sleep(2000);

    if (microphone_inference_start(EI_CLASSIFIER_SLICE_SIZE) == false) {
        ei_printf("ERR: Could not allocate audio buffer (size %d), this could be due to the window length of your model\r\n", EI_CLASSIFIER_RAW_SAMPLE_COUNT);
        return;
    }

    ei_printf("Recording...\n");
}

/**
 * @brief      Arduino main function. Runs the inferencing loop.
 */
void loop()
{
    bool m = microphone_inference_record();
    if (!m) {
        ei_printf("ERR: Failed to record audio...\n");
        return;
    }

    signal_t signal;
    signal.total_length = EI_CLASSIFIER_SLICE_SIZE;
    signal.get_data = &microphone_audio_signal_get_data;
    ei_impulse_result_t result = {0};

    EI_IMPULSE_ERROR r = run_classifier_continuous(&signal, &result, debug_nn);
    if (r != EI_IMPULSE_OK) {
        ei_printf("ERR: Failed to run classifier (%d)\n", r);
        return;
    }

    if (++print_results >= (EI_CLASSIFIER_SLICES_PER_MODEL_WINDOW)) {
        // print the predictions
        ei_printf("Predictions ");
        ei_printf("(DSP: %d ms., Classification: %d ms., Anomaly: %d ms.)",
            result.timing.dsp, result.timing.classification, result.timing.anomaly);
        ei_printf(": \n");
        for (size_t ix = 0; ix < EI_CLASSIFIER_LABEL_COUNT; ix++) {
            ei_printf("    %s: ", result.classification[ix].label);
            ei_printf_float(result.classification[ix].value);
            ei_printf("\n");
        }
#if EI_CLASSIFIER_HAS_ANOMALY == 1
        ei_printf("    anomaly score: ");
        ei_printf_float(result.anomaly);
        ei_printf("\n");
#endif

        print_results = 0;
    }
}

static void audio_inference_callback(uint32_t n_bytes)
{
    for(int i = 0; i < n_bytes>>1; i++) {
        inference.buffers[inference.buf_select][inference.buf_count++] = sampleBuffer[i];

        if(inference.buf_count >= inference.n_samples) {
            inference.buf_select ^= 1;
            inference.buf_count = 0;
            inference.buf_ready = 1;
        }
    }
}

static void capture_samples(void* arg) {

  const int32_t i2s_bytes_to_read = (uint32_t)arg;
  size_t bytes_read = i2s_bytes_to_read;

  while (record_status) {

    /* read data at once from i2s */
    i2s_read((i2s_port_t)1, (void*)sampleBuffer, i2s_bytes_to_read, &bytes_read, 100);

    if (bytes_read <= 0) {
      ei_printf("Error in I2S read : %d", bytes_read);
    }
    else {
        if (bytes_read < i2s_bytes_to_read) {
        ei_printf("Partial I2S read");
        }

        // scale the data (otherwise the sound is too quiet)
        for (int x = 0; x < i2s_bytes_to_read/2; x++) {
            sampleBuffer[x] = (int16_t)(sampleBuffer[x]) * 8;
        }

        if (record_status) {
            audio_inference_callback(i2s_bytes_to_read);
        }
        else {
            break;
        }
    }
  }
  vTaskDelete(NULL);
}

/**
 * @brief      Init inferencing struct and setup/start PDM
 *
 * @param[in]  n_samples  The n samples
 *
 * @return     { description_of_the_return_value }
 */
static bool microphone_inference_start(uint32_t n_samples)
{
    inference.buffers[0] = (signed short *)malloc(n_samples * sizeof(signed short));

    if (inference.buffers[0] == NULL) {
        return false;
    }

    inference.buffers[1] = (signed short *)malloc(n_samples * sizeof(signed short));

    if (inference.buffers[1] == NULL) {
        ei_free(inference.buffers[0]);
        return false;
    }

    inference.buf_select = 0;
    inference.buf_count = 0;
    inference.n_samples = n_samples;
    inference.buf_ready = 0;

    if (i2s_init(EI_CLASSIFIER_FREQUENCY)) {
        ei_printf("Failed to start I2S!");
    }

    ei_sleep(100);

    record_status = true;

    xTaskCreate(capture_samples, "CaptureSamples", 1024 * 32, (void*)sample_buffer_size, 10, NULL);

    return true;
}

/**
 * @brief      Wait on new data
 *
 * @return     True when finished
 */
static bool microphone_inference_record(void)
{
    bool ret = true;

    if (inference.buf_ready == 1) {
        ei_printf(
            "Error sample buffer overrun. Decrease the number of slices per model window "
            "(EI_CLASSIFIER_SLICES_PER_MODEL_WINDOW)\n");
        ret = false;
    }

    while (inference.buf_ready == 0) {
        delay(1);
    }

    inference.buf_ready = 0;
    return true;
}

/**
 * Get raw audio signal data
 */
static int microphone_audio_signal_get_data(size_t offset, size_t length, float *out_ptr)
{
    numpy::int16_to_float(&inference.buffers[inference.buf_select ^ 1][offset], out_ptr, length);

    return 0;
}

/**
 * @brief      Stop PDM and release buffers
 */
static void microphone_inference_end(void)
{
    i2s_deinit();
    ei_free(inference.buffers[0]);
    ei_free(inference.buffers[1]);
}


static int i2s_init(uint32_t sampling_rate) {
  // Start listening for audio: MONO @ 8/16KHz
  i2s_config_t i2s_config = {
      .mode = (i2s_mode_t)(I2S_MODE_MASTER | I2S_MODE_RX | I2S_MODE_TX),
      .sample_rate = sampling_rate,
      .bits_per_sample = (i2s_bits_per_sample_t)16,
      .channel_format = I2S_CHANNEL_FMT_ONLY_RIGHT,
      .communication_format = I2S_COMM_FORMAT_I2S,
      .intr_alloc_flags = 0,
      .dma_buf_count = 8,
      .dma_buf_len = 512,
      .use_apll = false,
      .tx_desc_auto_clear = false,
      .fixed_mclk = -1,
  };
  i2s_pin_config_t pin_config = {
      .bck_io_num = 26,    // IIS_SCLK
      .ws_io_num = 32,     // IIS_LCLK
      .data_out_num = -1,  // IIS_DSIN
      .data_in_num = 33,   // IIS_DOUT
  };
  esp_err_t ret = 0;

  ret = i2s_driver_install((i2s_port_t)1, &i2s_config, 0, NULL);
  if (ret != ESP_OK) {
    ei_printf("Error in i2s_driver_install");
  }

  ret = i2s_set_pin((i2s_port_t)1, &pin_config);
  if (ret != ESP_OK) {
    ei_printf("Error in i2s_set_pin");
  }

  ret = i2s_zero_dma_buffer((i2s_port_t)1);
  if (ret != ESP_OK) {
    ei_printf("Error in initializing dma buffer with 0");
  }

  return int(ret);
}

static int i2s_deinit(void) {
    i2s_driver_uninstall((i2s_port_t)1); //stop & destroy i2s driver
    return 0;
}

#if !defined(EI_CLASSIFIER_SENSOR) || EI_CLASSIFIER_SENSOR != EI_CLASSIFIER_SENSOR_MICROPHONE
#error "Invalid model for current sensor."
#endif

Credits

Sai Yamanoor

Sai Yamanoor

11 projects • 10 followers
I am a hardware engineer. I like to design PCBs and build exciting gadgets.

Comments