【Follow me第二季第4期】基于 Edge Impulse 的语音识别

eew_uscYT9

【Follow me第二季第4期】基于 Edge Impulse 的语音识别 [复制链接]

 

本项目教你如何做出自己的语音识别

本项目的大体流程

  我的语音识别是识别开灯和关灯两个声音，听到对应的声音就对板子上的灯进行开和关

 

https://studio.edgeimpulse.com/ 先去这个网站注册好账号

然后创建一个新的项目

   

输入项目名字，其他保存不动

接着到了数据的采集，我通过对Edge Impulse的文档查阅，发现可以用Arduino Nano主板进行数据的采集，其他的数据采集方式有手机、Edge Impulse CLI（该方式比较复杂）

先下载Edge Impulse准备好的固件

raspberry-rp2040.zip (349.95 KB, 下载次数: 0)

2024-12-26 19:03 上传

点击文件名下载附件

然后把该固件下载到nano板子上

接着点左边的data acquisition

  点击下面所指的图标就能进行数据的采集，数据分为训练数据集和测试数据集，一般是8、2开，

  数据采集完之后点击creat impulse进行训练的设置，如下面所示，设置完之后点击save impulse

  点击mfcc进行参数的设置，直接默认设置，然后保存参数

  然后点击上方的generate features进行生成特征 ，根据feature explorer能够看出我的数据区分度还是挺高的

  接着点击classifier 进行训练，参数都可以用默认设置

  点击model  testing进行模型测试 我的模型训练还是可以的   接下来进行模型的部署，我们现在arduino，然后进行build，把生成的文件下载下来，打开arduino ide进行添加

  我的代码如下

/* Edge Impulse ingestion SDK
 * Copyright (c) 2022 EdgeImpulse Inc.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 * http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 *
 */

// 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 <rp2040_inferencing.h>
#include <PDM.h>
#include "WiFiNINA.h"

#define led1 LEDB
#define led2 LEDG
#define led3 LEDR

/** Audio buffers, pointers and selectors */
typedef struct {
    int16_t *buffer;
    uint8_t buf_ready;
    uint32_t buf_count;
    uint32_t n_samples;
} inference_t;

static inference_t inference;
static signed short sampleBuffer[2048];
static bool debug_nn = false; // Set this to true to see e.g. features generated from the raw signal
static volatile bool record_ready = false;

/**
 * [url=home.php?mod=space&uid=159083]@brief[/url]  Arduino setup function
 */
void setup()
{
    // put your setup code here, to run once:
    Serial.begin(115200);
    pinMode(led3, OUTPUT);
    pinMode(led2, OUTPUT);
    // 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]));

    if (microphone_inference_start(EI_CLASSIFIER_RAW_SAMPLE_COUNT) == 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;
    }
}

/**
 * @brief      Arduino main function. Runs the inferencing loop.
 */
void loop()
{
    ei_printf("Starting inferencing in 2 seconds...\n");

    delay(2000);

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

    bool m = microphone_inference_record();
    if (!m) {
        ei_printf("ERR: Failed to record audio...\n");
        return;
    }

    ei_printf("Recording done\n");

    signal_t signal;
    signal.total_length = EI_CLASSIFIER_RAW_SAMPLE_COUNT;
    signal.get_data = µphone_audio_signal_get_data;
    ei_impulse_result_t result = { 0 };

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

    // print inference return code
    ei_printf("run_classifier returned: %d\r\n", res);
    print_inference_result(result);
  
    //ei_printf("  %s: ", ei_classifier_inferencing_categories[i]);
}

/**
 * @brief      PDM buffer full callback
 *             Copy audio data to app buffers
 */
static void pdm_data_ready_inference_callback(void)
{
    int bytesAvailable = PDM.available();

    // read into the sample buffer
    int bytesRead = PDM.read((char *)&sampleBuffer[0], bytesAvailable);

    if ((inference.buf_ready == 0) && (record_ready == true)) {

        for(int i = 0; i < bytesRead>>1; i++) {
            inference.buffer[inference.buf_count++] = sampleBuffer[i];

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

/**
 * @brief      Init inferencing struct and setup/start PDM
 *
 * @param[in]  n_samples  The n samples
 *
 * [url=home.php?mod=space&uid=784970]@return[/url]  { description_of_the_return_value }
 */
static bool microphone_inference_start(uint32_t n_samples)
{
    inference.buffer = (int16_t *)malloc(n_samples * sizeof(int16_t));

    if(inference.buffer == NULL) {
        return false;
    }

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

    // configure the data receive callback
    PDM.onReceive(pdm_data_ready_inference_callback);

    PDM.setBufferSize(2048);
    delay(250);

    // initialize PDM with:
    // - one channel (mono mode)
    if (!PDM.begin(1, EI_CLASSIFIER_FREQUENCY)) {
        ei_printf("ERR: Failed to start PDM!");
        microphone_inference_end();
        return false;
    }

    // optionally set the gain, defaults to 24
    // Note: values >=52 not supported
    //PDM.setGain(40);

    return true;
}

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

    record_ready = true;
    while (inference.buf_ready == 0) {
        delay(10);
    }

    inference.buf_ready = 0;
    record_ready = false;

    return ret;
}

/**
 * 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.buffer[offset], out_ptr, length);

    return 0;
}

/**
 * @brief      Stop PDM and release buffers
 */
static void microphone_inference_end(void)
{
    PDM.end();
    ei_free(inference.buffer);
}

void print_inference_result(ei_impulse_result_t result) {

    // Print how long it took to perform inference
    ei_printf("Timing: DSP %d ms, inference %d ms, anomaly %d ms\r\n",
            result.timing.dsp,
            result.timing.classification,
            result.timing.anomaly);

    ei_printf("Predictions:\r\n");
    for (uint16_t i = 0; i < EI_CLASSIFIER_LABEL_COUNT; i++) {
      if(result.classification[i].value>0.7)
        {
          switch (i) {
            case 0: digitalWrite(led3, LOW); break;
            case 1: digitalWrite(led3, HIGH); break;
            
            default: digitalWrite(led2, LOW);
          }

        }
          
        ei_printf("  %s: ", ei_classifier_inferencing_categories[i]);
        ei_printf("%.5f\r\n", result.classification[i].value);
    }

    // Print anomaly result (if it exists)
#if EI_CLASSIFIER_HAS_ANOMALY == 1
    ei_printf("Anomaly prediction: %.3f\r\n", result.anomaly);
#endif

}

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

 

演示视频

VID_20241226_212700

 

 

 

Jacktang

好吧，已经能识别开灯和关灯两个声音了，不错嘛

lugl4313820

咱们这个语音识别，是要联网？还是把算法下载到本地就可以识别了？

L物恩纶

干得好