forked from xiaozhi/xiaozhi-esp32
2b025c4ea6
* Enhance audio processing and wake word detection - Set task priority in Application::Run to improve responsiveness. - Log detected wake words with their state in HandleWakeWordDetectedEvent. - Streamline audio feeding in AudioService to handle both wake word and audio processor events. - Implement input buffering in AfeAudioProcessor, AfeWakeWord, CustomWakeWord, and EspWakeWord to manage audio data more efficiently. - Clear input buffers on stop to prevent residual data issues. * Refactor audio processing to enhance thread safety and state management - Implement early return checks in Feed methods of AfeAudioProcessor, AfeWakeWord, CustomWakeWord, and EspWakeWord to prevent processing when not running. - Introduce std::atomic for running state in CustomWakeWord and EspWakeWord to ensure thread-safe access. - Consolidate input buffer management with mutex locks to avoid race conditions during Stop and Feed operations. * Refactor listening mode handling and wake word detection configuration - Replace direct mode setting logic with a new GetDefaultListeningMode method for improved clarity and maintainability. - Update HandleToggleChatEvent, HandleWakeWordDetectedEvent, and ContinueWakeWordInvoke to utilize the new method for determining listening mode. - Introduce Kconfig option WAKE_WORD_DETECTION_IN_LISTENING to enable or disable wake word detection during listening mode, enhancing configurability.
48 lines
1.4 KiB
C++
48 lines
1.4 KiB
C++
#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 <mutex>
|
|
|
|
#include "audio_processor.h"
|
|
#include "audio_codec.h"
|
|
|
|
class AfeAudioProcessor : public AudioProcessor {
|
|
public:
|
|
AfeAudioProcessor();
|
|
~AfeAudioProcessor();
|
|
|
|
void Initialize(AudioCodec* codec, int frame_duration_ms, srmodel_list_t* models_list) override;
|
|
void Feed(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;
|
|
const 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;
|
|
int frame_samples_ = 0;
|
|
bool is_speaking_ = false;
|
|
std::vector<int16_t> input_buffer_;
|
|
std::mutex input_buffer_mutex_;
|
|
std::vector<int16_t> output_buffer_;
|
|
|
|
void AudioProcessorTask();
|
|
};
|
|
|
|
#endif |