MakerGram Logo

    MakerGram
    • Register
    • Login
    • Search
    • Categories
    • Recent
    • Popular
    • Tags
    • Users
    • Groups

    AI enabled acoustic object detection system

    TinyML
    2
    2
    129
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • S
      sanal143 last edited by sanal143

      I'm developing an audio classification project with four classes using an RNN with LSTM. While the model performs well in classifying audio in silent environments, it struggles with noisy situations like crowds or disturbances. How can I train the model more robustly to accurately predict classifications in such challenging environments?

      salmanfaris 1 Reply Last reply Reply Quote 0
      • salmanfaris
        salmanfaris @sanal143 last edited by

        Hi @sanal143, Welcome to the MakerGram community ✨.

        Does your training data contain noise data similar to the data you are inferencing? and May I know, what kind of hardware you are using to run the model. Thanks

        1 Reply Last reply Reply Quote 0
        • First post
          Last post

        Recent Posts

        • Hi @sanal143, Welcome to the MakerGram community ✨.

          Does your training data contain noise data similar to the data you are inferencing? and May I know, what kind of hardware you are using to run the model. Thanks

          • read more
        • S

          I'm developing an audio classification project with four classes using an RNN with LSTM. While the model performs well in classifying audio in silent environments, it struggles with noisy situations like crowds or disturbances. How can I train the model more robustly to accurately predict classifications in such challenging environments?

          • read more
        • A

          @salmanfaris No, I haven't made any progess on the matter

          • read more

        • Hi @amalkrishnam3, Were you able to make any progress?

          • read more
        • A

          I have been working on a project . In which I want to capture data using the PDM mic and trasmit it through the BLE available . I am new to hardware and these sensors so I am unable to make sense of the data I am reciving on the other side(central) that is my mobile device(iphone X) with BlueLight application. I am able to find a service and I am reciving some form of hex code,but I don't know how to convert it to wave files or don't know whether it's possible or not .

          If you guys have any idea or any resources that could help please do share.

          I am attaching my code below :

          #include <ArduinoBLE.h> #include <mic.h> // microphone library // Microphone Settings #define DEBUG 1 #define SAMPLES 800 mic_config_t mic_config = { .channel_cnt = 1, .sampling_rate = 16000, .buf_size = 1600, .debug_pin = LED_BUILTIN }; NRF52840_ADC_Class Mic(&mic_config); int16_t recording_buf[SAMPLES]; volatile static bool record_ready = false; // Updated UUIDs #define SERVICE_UUID "19B10000-E8F2-537E-4F6C-D104768A1214" #define CHARACTERISTIC_UUID_AUDIO "19B10001-E8F2-537E-4F6C-D104768A1214" // BLE Service and Characteristic BLEService audioService(SERVICE_UUID); // Corrected initialization with explicit value size and fixed length flag BLECharacteristic audioDataCharacteristic(CHARACTERISTIC_UUID_AUDIO, BLERead | BLENotify | BLEWrite, sizeof(recording_buf), true); void setup() { Serial.begin(115200); while (!Serial) delay(10); Serial.println("Initializing microphone..."); Mic.set_callback(audio_rec_callback); if (!Mic.begin()) { Serial.println("Mic initialization failed"); while (1); } Serial.println("Mic initialized."); Serial.println("Initializing BLE..."); if (!BLE.begin()) { Serial.println("Failed to start BLE!"); while (1); } BLE.setLocalName("SCT Audio"); BLE.setAdvertisedService(audioService); audioService.addCharacteristic(audioDataCharacteristic); BLE.addService(audioService); // Corrected writeValue call with explicit casting audioDataCharacteristic.writeValue((uint8_t)0); BLE.advertise(); Serial.println("BLE Peripheral is now advertising"); } void loop() { BLEDevice central = BLE.central(); if (central) { Serial.println("Connected to central device"); while (central.connected()) { if (record_ready) { // Plot the audio data in the Serial Plotter for (int i = 0; i < SAMPLES; i++) { Serial.println(recording_buf[i]); } // Transmit the audio data audioDataCharacteristic.writeValue((uint8_t*)recording_buf, 2 * SAMPLES); Serial.println("Audio data transmitted over BLE"); record_ready = false; } } Serial.println("Disconnected from central device"); } } static void audio_rec_callback(uint16_t *buf, uint32_t buf_len) { static uint32_t idx = 0; for (uint32_t i = 0; i < buf_len; i++) { recording_buf[idx++] = buf[i]; if (idx >= SAMPLES){ idx = 0; record_ready = true; break; } } }

          • read more
        By MakerGram | A XiStart Initiative | Built with ♥ NodeBB
        Copyright © 2023 MakerGram, All rights reserved.
        Privacy Policy | Terms & Conditions | Disclaimer | Code of Conduct