mirror of
https://github.com/78/xiaozhi-esp32.git
synced 2026-07-21 02:05:52 +00:00
3e78cd73bd
* Migrate board builds to ESP-IDF 6.0.1 * Document upstream IDF 6 CI blockers * Use IDF 6 patched registry components * Fix board-specific ESP-IDF 6 build errors * Fix remaining ESP-IDF 6 board builds * Document final ESP-IDF 6 matrix results [skip ci] * update IDF 6 component releases * rebase IDF 6 migration and use upstream SSCMA * Enhance audio input management in AudioService - Introduced AS_EVENT_AUDIO_INPUT_STOP_REQUEST to manage audio input stopping more effectively. - Updated AudioService::Start() to clear the new stop request event. - Modified AudioService::AudioInputTask() to handle the stop request and ensure proper input disabling. - Adjusted AdcPdmAudioCodec::Start() to reflect lazy input opening, ensuring start/stop operations run in the same task. * Refactor audio codec management and configuration - Added output_device_opened_ flag to track the state of the output device in Es8388 and Es8389 codecs. - Updated EnableOutput method to prevent unnecessary device reopening and added mute functionality to manage audio output more effectively. - Enhanced error handling in Es8311AudioCodec by ensuring proper closure and deletion of the codec device. - Adjusted sample rates in board configurations for atk-dnesp32s3-box2 to 24000 Hz and introduced AUDIO_CODEC_USE_MCLK for improved clock management. * Update build configurations and documentation for ESP-IDF 6 compatibility - Added container specification for the build workflow using espressif/idf:v6.0.1. - Updated the version of the espressif/esp_video component to ^2.3.0. - Enhanced documentation to clarify the support status of ESP32-P4 variants, specifying that legacy Rev < 3 variants are excluded from the IDF 6 matrix. - Adjusted board configurations to include IDF version constraints and necessary SDK configurations for legacy support. - Improved handling of YUV formats in EspVideo to maintain compatibility with previous versions. * Implement playback drained event handling in Application - Added MAIN_EVENT_PLAYBACK_DRAINED to manage playback state transitions. - Introduced callbacks for playback drained events in AudioService to trigger listening state changes. - Refactored Application::Run() to handle deferred listening start based on playback queue status. - Enhanced audio processing logic to prevent audio truncation during state changes. - Updated related methods to ensure proper wake word detection configuration during listening mode. * Fix variant selection shell in CI * Update project version to 2.4.0 and adjust component dependencies - Bump project version in CMakeLists.txt to 2.4.0. - Change espressif/esp_video component version to ^2.0.1 in idf_component.yml. - Modify AUDIO_INPUT_REFERENCE setting in config.h to false for m5stack-core-s3. - Remove unnecessary infinite loops in xmini_c3_board.cc during initialization. --------- Co-authored-by: Xiaoxia <terrence.huang@tenclass.com>
107 lines
3.7 KiB
C++
107 lines
3.7 KiB
C++
#ifndef AFE_AUDIO_ENGINE_H
|
|
#define AFE_AUDIO_ENGINE_H
|
|
|
|
#include <atomic>
|
|
#include <condition_variable>
|
|
#include <deque>
|
|
#include <functional>
|
|
#include <memory>
|
|
#include <mutex>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
#include <esp_afe_sr_models.h>
|
|
#include <freertos/FreeRTOS.h>
|
|
#include <freertos/event_groups.h>
|
|
#include <freertos/task.h>
|
|
|
|
#include "audio_engine.h"
|
|
#include "wake_words/wake_word_audio_cache.h"
|
|
|
|
class CustomWakeWord;
|
|
|
|
class AfeAudioEngine : public AudioEngine {
|
|
public:
|
|
AfeAudioEngine();
|
|
~AfeAudioEngine() override;
|
|
|
|
bool Initialize(AudioCodec* codec, int frame_duration_ms, srmodel_list_t* models_list) override;
|
|
void Feed(std::vector<int16_t>&& data) override;
|
|
|
|
void EnableWakeWordDetection(bool enable) override;
|
|
void EnableVoiceProcessing(bool enable) override;
|
|
void EnableDeviceAec(bool enable) override;
|
|
|
|
bool HasWakeWord() const override;
|
|
bool IsWakeWordDetectionEnabled() const override;
|
|
bool IsVoiceProcessingEnabled() const override;
|
|
bool IsAfeWakeWord() const override { return HasWakeWord(); }
|
|
size_t GetFeedSize() const override;
|
|
|
|
void OnWakeWordDetected(std::function<void(const std::string& wake_word)> callback) override;
|
|
void OnOutput(std::function<void(std::vector<int16_t>&& data)> callback) override;
|
|
void OnVadStateChange(std::function<void(bool speaking)> callback) override;
|
|
|
|
void EncodeWakeWordData() override;
|
|
bool GetWakeWordOpus(std::vector<uint8_t>& opus) override;
|
|
const std::string& GetLastDetectedWakeWord() const override { return last_detected_wake_word_; }
|
|
|
|
private:
|
|
enum class WakeDetector {
|
|
kNone,
|
|
kWakeNet,
|
|
kMultiNet,
|
|
};
|
|
|
|
static constexpr EventBits_t kWakeWordEnabled = 1 << 0;
|
|
static constexpr EventBits_t kVoiceProcessingEnabled = 1 << 1;
|
|
static constexpr EventBits_t kAfeActive = 1 << 2;
|
|
|
|
AudioCodec* codec_ = nullptr;
|
|
srmodel_list_t* models_ = nullptr;
|
|
bool owns_models_ = false;
|
|
const esp_afe_sr_iface_t* afe_iface_ = nullptr;
|
|
esp_afe_sr_data_t* afe_data_ = nullptr;
|
|
EventGroupHandle_t event_group_ = nullptr;
|
|
TaskHandle_t processing_task_ = nullptr;
|
|
int frame_samples_ = 0;
|
|
bool is_speaking_ = false;
|
|
bool device_aec_enabled_ = false;
|
|
// Deferred AFE buffer reset, performed by ProcessingTask (see UpdateActiveState)
|
|
std::atomic<bool> reset_pending_{false};
|
|
// Deferred WakeNet/AEC toggles, applied by ProcessingTask (see ApplyAfeControls)
|
|
std::atomic<bool> afe_control_dirty_{false};
|
|
// Deferred output_buffer_ clear, performed by the output-producing task
|
|
std::atomic<bool> output_reset_pending_{false};
|
|
WakeDetector wake_detector_ = WakeDetector::kNone;
|
|
|
|
std::unique_ptr<CustomWakeWord> custom_wake_word_;
|
|
std::vector<std::string> wake_words_;
|
|
std::string last_detected_wake_word_;
|
|
std::vector<int16_t> input_buffer_;
|
|
std::vector<int16_t> output_buffer_;
|
|
std::mutex input_buffer_mutex_;
|
|
|
|
std::function<void(const std::string&)> wake_word_detected_callback_;
|
|
std::function<void(std::vector<int16_t>&&)> output_callback_;
|
|
std::function<void(bool)> vad_state_change_callback_;
|
|
|
|
TaskHandle_t wake_word_encode_task_ = nullptr;
|
|
StaticTask_t* wake_word_encode_task_buffer_ = nullptr;
|
|
StackType_t* wake_word_encode_task_stack_ = nullptr;
|
|
WakeWordAudioCache wake_word_audio_cache_;
|
|
std::deque<std::vector<uint8_t>> wake_word_opus_;
|
|
std::mutex wake_word_mutex_;
|
|
std::condition_variable wake_word_cv_;
|
|
|
|
void ProcessingTask();
|
|
void UpdateActiveState();
|
|
void UpdateAecState();
|
|
void ApplyAfeControls();
|
|
void OutputRawAudio(const std::vector<int16_t>& data);
|
|
void HandleWakeWordResult(const afe_fetch_result_t* result);
|
|
void HandleVoiceResult(const afe_fetch_result_t* result);
|
|
};
|
|
|
|
#endif
|