v1.8.0: Audio 代码重构与低功耗优化 (#943)

* Reconstruct Audio Code

* Remove old IoT implementation

* Add MQTT-UDP documentation

* OTA升级失败时，可以继续使用

main/audio/processors/afe_audio_processor.cc

@@ -0,0 +1,161 @@
+#include "afe_audio_processor.h"
+#include <esp_log.h>
+
+#define PROCESSOR_RUNNING 0x01
+
+#define TAG "AfeAudioProcessor"
+
+AfeAudioProcessor::AfeAudioProcessor()
+    : afe_data_(nullptr) {
+    event_group_ = xEventGroupCreate();
+}
+
+void AfeAudioProcessor::Initialize(AudioCodec* codec) {
+    codec_ = codec;
+    int ref_num = codec_->input_reference() ? 1 : 0;
+
+    std::string input_format;
+    for (int i = 0; i < codec_->input_channels() - ref_num; i++) {
+        input_format.push_back('M');
+    }
+    for (int i = 0; i < ref_num; i++) {
+        input_format.push_back('R');
+    }
+
+    srmodel_list_t *models = esp_srmodel_init("model");
+    char* ns_model_name = esp_srmodel_filter(models, ESP_NSNET_PREFIX, NULL);
+    char* vad_model_name = esp_srmodel_filter(models, ESP_VADN_PREFIX, NULL);
+    
+    afe_config_t* afe_config = afe_config_init(input_format.c_str(), NULL, AFE_TYPE_VC, AFE_MODE_HIGH_PERF);
+    afe_config->aec_mode = AEC_MODE_VOIP_HIGH_PERF;
+    afe_config->vad_mode = VAD_MODE_0;
+    afe_config->vad_min_noise_ms = 100;
+    if (vad_model_name != nullptr) {
+        afe_config->vad_model_name = vad_model_name;
+    }
+
+    if (ns_model_name != nullptr) {
+        afe_config->ns_init = true;
+        afe_config->ns_model_name = ns_model_name;
+        afe_config->afe_ns_mode = AFE_NS_MODE_NET;
+    } else {
+        afe_config->ns_init = false;
+    }
+
+    afe_config->afe_perferred_core = 1;
+    afe_config->afe_perferred_priority = 1;
+    afe_config->agc_init = false;
+    afe_config->memory_alloc_mode = AFE_MEMORY_ALLOC_MORE_PSRAM;
+
+#ifdef CONFIG_USE_DEVICE_AEC
+    afe_config->aec_init = true;
+    afe_config->vad_init = false;
+#else
+    afe_config->aec_init = false;
+    afe_config->vad_init = true;
+#endif
+
+    afe_iface_ = esp_afe_handle_from_config(afe_config);
+    afe_data_ = afe_iface_->create_from_config(afe_config);
+    
+    xTaskCreate([](void* arg) {
+        auto this_ = (AfeAudioProcessor*)arg;
+        this_->AudioProcessorTask();
+        vTaskDelete(NULL);
+    }, "audio_communication", 4096, this, 3, NULL);
+}
+
+AfeAudioProcessor::~AfeAudioProcessor() {
+    if (afe_data_ != nullptr) {
+        afe_iface_->destroy(afe_data_);
+    }
+    vEventGroupDelete(event_group_);
+}
+
+size_t AfeAudioProcessor::GetFeedSize() {
+    if (afe_data_ == nullptr) {
+        return 0;
+    }
+    return afe_iface_->get_feed_chunksize(afe_data_) * codec_->input_channels();
+}
+
+void AfeAudioProcessor::Feed(const std::vector<int16_t>& data) {
+    if (afe_data_ == nullptr) {
+        return;
+    }
+    afe_iface_->feed(afe_data_, data.data());
+}
+
+void AfeAudioProcessor::Start() {
+    xEventGroupSetBits(event_group_, PROCESSOR_RUNNING);
+}
+
+void AfeAudioProcessor::Stop() {
+    xEventGroupClearBits(event_group_, PROCESSOR_RUNNING);
+    if (afe_data_ != nullptr) {
+        afe_iface_->reset_buffer(afe_data_);
+    }
+}
+
+bool AfeAudioProcessor::IsRunning() {
+    return xEventGroupGetBits(event_group_) & PROCESSOR_RUNNING;
+}
+
+void AfeAudioProcessor::OnOutput(std::function<void(std::vector<int16_t>&& data)> callback) {
+    output_callback_ = callback;
+}
+
+void AfeAudioProcessor::OnVadStateChange(std::function<void(bool speaking)> callback) {
+    vad_state_change_callback_ = callback;
+}
+
+void AfeAudioProcessor::AudioProcessorTask() {
+    auto fetch_size = afe_iface_->get_fetch_chunksize(afe_data_);
+    auto feed_size = afe_iface_->get_feed_chunksize(afe_data_);
+    ESP_LOGI(TAG, "Audio communication task started, feed size: %d fetch size: %d",
+        feed_size, fetch_size);
+
+    while (true) {
+        xEventGroupWaitBits(event_group_, PROCESSOR_RUNNING, pdFALSE, pdTRUE, portMAX_DELAY);
+
+        auto res = afe_iface_->fetch_with_delay(afe_data_, portMAX_DELAY);
+        if ((xEventGroupGetBits(event_group_) & PROCESSOR_RUNNING) == 0) {
+            continue;
+        }
+        if (res == nullptr || res->ret_value == ESP_FAIL) {
+            if (res != nullptr) {
+                ESP_LOGI(TAG, "Error code: %d", res->ret_value);
+            }
+            continue;
+        }
+
+        // VAD state change
+        if (vad_state_change_callback_) {
+            if (res->vad_state == VAD_SPEECH && !is_speaking_) {
+                is_speaking_ = true;
+                vad_state_change_callback_(true);
+            } else if (res->vad_state == VAD_SILENCE && is_speaking_) {
+                is_speaking_ = false;
+                vad_state_change_callback_(false);
+            }
+        }
+
+        if (output_callback_) {
+            output_callback_(std::vector<int16_t>(res->data, res->data + res->data_size / sizeof(int16_t)));
+        }
+    }
+}
+
+void AfeAudioProcessor::EnableDeviceAec(bool enable) {
+    if (enable) {
+#if CONFIG_USE_DEVICE_AEC
+        afe_iface_->disable_vad(afe_data_);
+        afe_iface_->enable_aec(afe_data_);
+#else
+        ESP_LOGE(TAG, "Device AEC is not supported");
+#endif
+    } else {
+        afe_iface_->disable_aec(afe_data_);
+        afe_iface_->enable_vad(afe_data_);
+    }
+}

main/audio/processors/afe_audio_processor.h

@@ -0,0 +1,43 @@
+#ifndef AFE_AUDIO_PROCESSOR_H
+#define AFE_AUDIO_PROCESSOR_H
+
+#include <esp_afe_sr_models.h>
+#include <freertos/FreeRTOS.h>
+#include <freertos/task.h>
+#include <freertos/event_groups.h>
+
+#include <string>
+#include <vector>
+#include <functional>
+
+#include "audio_processor.h"
+#include "audio_codec.h"
+
+class AfeAudioProcessor : public AudioProcessor {
+public:
+    AfeAudioProcessor();
+    ~AfeAudioProcessor();
+
+    void Initialize(AudioCodec* codec) override;
+    void Feed(const std::vector<int16_t>& data) override;
+    void Start() override;
+    void Stop() override;
+    bool IsRunning() override;
+    void OnOutput(std::function<void(std::vector<int16_t>&& data)> callback) override;
+    void OnVadStateChange(std::function<void(bool speaking)> callback) override;
+    size_t GetFeedSize() override;
+    void EnableDeviceAec(bool enable) override;
+
+private:
+    EventGroupHandle_t event_group_ = nullptr;
+    esp_afe_sr_iface_t* afe_iface_ = nullptr;
+    esp_afe_sr_data_t* afe_data_ = nullptr;
+    std::function<void(std::vector<int16_t>&& data)> output_callback_;
+    std::function<void(bool speaking)> vad_state_change_callback_;
+    AudioCodec* codec_ = nullptr;
+    bool is_speaking_ = false;
+
+    void AudioProcessorTask();
+};
+
+#endif 

main/audio/processors/audio_debugger.cc

@@ -0,0 +1,68 @@
+#include "audio_debugger.h"
+#include "sdkconfig.h"
+
+#if CONFIG_USE_AUDIO_DEBUGGER
+#include <esp_log.h>
+#include <arpa/inet.h>
+#include <unistd.h>
+#include <errno.h>
+#include <cstring>
+#include <string>
+#endif
+
+#define TAG "AudioDebugger"
+
+
+AudioDebugger::AudioDebugger() {
+#if CONFIG_USE_AUDIO_DEBUGGER
+    udp_sockfd_ = socket(AF_INET, SOCK_DGRAM, 0);
+    if (udp_sockfd_ >= 0) {
+        // 解析配置的服务器地址 "IP:PORT"
+        std::string server_addr = CONFIG_AUDIO_DEBUG_UDP_SERVER;
+        size_t colon_pos = server_addr.find(':');
+        
+        if (colon_pos != std::string::npos) {
+            std::string ip = server_addr.substr(0, colon_pos);
+            int port = std::stoi(server_addr.substr(colon_pos + 1));
+            
+            memset(&udp_server_addr_, 0, sizeof(udp_server_addr_));
+            udp_server_addr_.sin_family = AF_INET;
+            udp_server_addr_.sin_port = htons(port);
+            inet_pton(AF_INET, ip.c_str(), &udp_server_addr_.sin_addr);
+            
+            ESP_LOGI(TAG, "Initialized server address: %s", CONFIG_AUDIO_DEBUG_UDP_SERVER);
+        } else {
+            ESP_LOGW(TAG, "Invalid server address: %s, should be IP:PORT", CONFIG_AUDIO_DEBUG_UDP_SERVER);
+            close(udp_sockfd_);
+            udp_sockfd_ = -1;
+        }
+    } else {
+        ESP_LOGW(TAG, "Failed to create UDP socket: %d", errno);
+    }
+#endif
+}
+
+AudioDebugger::~AudioDebugger() {
+#if CONFIG_USE_AUDIO_DEBUGGER
+    if (udp_sockfd_ >= 0) {
+        close(udp_sockfd_);
+        ESP_LOGI(TAG, "Closed UDP socket");
+    }
+#endif
+}
+
+void AudioDebugger::Feed(const std::vector<int16_t>& data) {
+#if CONFIG_USE_AUDIO_DEBUGGER
+    if (udp_sockfd_ >= 0) {
+        ssize_t sent = sendto(udp_sockfd_, data.data(), data.size() * sizeof(int16_t), 0,
+                             (struct sockaddr*)&udp_server_addr_, sizeof(udp_server_addr_));
+        if (sent < 0) {
+            ESP_LOGW(TAG, "Failed to send audio data to %s: %d", CONFIG_AUDIO_DEBUG_UDP_SERVER, errno);
+        } else {
+            ESP_LOGD(TAG, "Sent %d bytes audio data to %s", sent, CONFIG_AUDIO_DEBUG_UDP_SERVER);
+        }
+    }
+#endif
+}
+
+ 

main/audio/processors/audio_debugger.h

@@ -0,0 +1,22 @@
+#ifndef AUDIO_DEBUGGER_H
+#define AUDIO_DEBUGGER_H
+
+#include <vector>
+#include <cstdint>
+
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+class AudioDebugger {
+public:
+    AudioDebugger();
+    ~AudioDebugger();
+
+    void Feed(const std::vector<int16_t>& data);
+
+private:
+    int udp_sockfd_ = -1;
+    struct sockaddr_in udp_server_addr_;
+};
+
+#endif 

main/audio/processors/no_audio_processor.cc

@@ -0,0 +1,50 @@
+#include "no_audio_processor.h"
+#include <esp_log.h>
+
+#define TAG "NoAudioProcessor"
+
+void NoAudioProcessor::Initialize(AudioCodec* codec) {
+    codec_ = codec;
+}
+
+void NoAudioProcessor::Feed(const std::vector<int16_t>& data) {
+    if (!is_running_ || !output_callback_) {
+        return;
+    }
+    // 直接将输入数据传递给输出回调
+    output_callback_(std::vector<int16_t>(data));
+}
+
+void NoAudioProcessor::Start() {
+    is_running_ = true;
+}
+
+void NoAudioProcessor::Stop() {
+    is_running_ = false;
+}
+
+bool NoAudioProcessor::IsRunning() {
+    return is_running_;
+}
+
+void NoAudioProcessor::OnOutput(std::function<void(std::vector<int16_t>&& data)> callback) {
+    output_callback_ = callback;
+}
+
+void NoAudioProcessor::OnVadStateChange(std::function<void(bool speaking)> callback) {
+    vad_state_change_callback_ = callback;
+}
+
+size_t NoAudioProcessor::GetFeedSize() {
+    if (!codec_) {
+        return 0;
+    }
+    // 返回一个固定的帧大小，比如 30ms 的数据
+    return 30 * codec_->input_sample_rate() / 1000;
+}
+
+void NoAudioProcessor::EnableDeviceAec(bool enable) {
+    if (enable) {
+        ESP_LOGE(TAG, "Device AEC is not supported");
+    }
+}

main/audio/processors/no_audio_processor.h

@@ -0,0 +1,32 @@
+#ifndef DUMMY_AUDIO_PROCESSOR_H
+#define DUMMY_AUDIO_PROCESSOR_H
+
+#include <vector>
+#include <functional>
+
+#include "audio_processor.h"
+#include "audio_codec.h"
+
+class NoAudioProcessor : public AudioProcessor {
+public:
+    NoAudioProcessor() = default;
+    ~NoAudioProcessor() = default;
+
+    void Initialize(AudioCodec* codec) override;
+    void Feed(const std::vector<int16_t>& data) override;
+    void Start() override;
+    void Stop() override;
+    bool IsRunning() override;
+    void OnOutput(std::function<void(std::vector<int16_t>&& data)> callback) override;
+    void OnVadStateChange(std::function<void(bool speaking)> callback) override;
+    size_t GetFeedSize() override;
+    void EnableDeviceAec(bool enable) override;
+
+private:
+    AudioCodec* codec_ = nullptr;
+    std::function<void(std::vector<int16_t>&& data)> output_callback_;
+    std::function<void(bool speaking)> vad_state_change_callback_;
+    bool is_running_ = false;
+};
+
+#endif