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.
63 lines
1.8 KiB
C++
63 lines
1.8 KiB
C++
#ifndef AFE_WAKE_WORD_H
|
|
#define AFE_WAKE_WORD_H
|
|
|
|
#include <freertos/FreeRTOS.h>
|
|
#include <freertos/task.h>
|
|
#include <freertos/event_groups.h>
|
|
|
|
#include <esp_afe_sr_models.h>
|
|
#include <esp_nsn_models.h>
|
|
#include <model_path.h>
|
|
|
|
#include <deque>
|
|
#include <string>
|
|
#include <vector>
|
|
#include <functional>
|
|
#include <mutex>
|
|
#include <condition_variable>
|
|
|
|
#include "audio_codec.h"
|
|
#include "wake_word.h"
|
|
|
|
class AfeWakeWord : public WakeWord {
|
|
public:
|
|
AfeWakeWord();
|
|
~AfeWakeWord();
|
|
|
|
bool Initialize(AudioCodec* codec, srmodel_list_t* models_list);
|
|
void Feed(const std::vector<int16_t>& data);
|
|
void OnWakeWordDetected(std::function<void(const std::string& wake_word)> callback);
|
|
void Start();
|
|
void Stop();
|
|
size_t GetFeedSize();
|
|
void EncodeWakeWordData();
|
|
bool GetWakeWordOpus(std::vector<uint8_t>& opus);
|
|
const std::string& GetLastDetectedWakeWord() const { return last_detected_wake_word_; }
|
|
|
|
private:
|
|
srmodel_list_t *models_ = nullptr;
|
|
const esp_afe_sr_iface_t* afe_iface_ = nullptr;
|
|
esp_afe_sr_data_t* afe_data_ = nullptr;
|
|
char* wakenet_model_ = NULL;
|
|
std::vector<std::string> wake_words_;
|
|
EventGroupHandle_t event_group_;
|
|
std::function<void(const std::string& wake_word)> wake_word_detected_callback_;
|
|
AudioCodec* codec_ = nullptr;
|
|
std::string last_detected_wake_word_;
|
|
std::vector<int16_t> input_buffer_;
|
|
std::mutex input_buffer_mutex_;
|
|
|
|
TaskHandle_t wake_word_encode_task_ = nullptr;
|
|
StaticTask_t* wake_word_encode_task_buffer_ = nullptr;
|
|
StackType_t* wake_word_encode_task_stack_ = nullptr;
|
|
std::deque<std::vector<int16_t>> wake_word_pcm_;
|
|
std::deque<std::vector<uint8_t>> wake_word_opus_;
|
|
std::mutex wake_word_mutex_;
|
|
std::condition_variable wake_word_cv_;
|
|
|
|
void StoreWakeWordData(const int16_t* data, size_t size);
|
|
void AudioDetectionTask();
|
|
};
|
|
|
|
#endif
|