feat: add vad reset func

docs/en/audio_front_end/README.rst

@@ -54,15 +54,17 @@ Input Format Definition
 
 The ``input_format`` parameter specifies the arrangement of audio channels in the input data. Each character in the string represents a channel type:
 
-+-----------+-------------+
++-----------+---------------------+
-| Character | Description |
+| Character | Description         |
-+===========+=============+
++===========+=====================+
-| ``M``     | Microphone channel |
+| ``M``     | Microphone channel  |
-+-----------+-------------+
++-----------+---------------------+
-| ``R``     | Playback reference channel |
+| ``R``     | Playback reference  |
-+-----------+-------------+
+|           | channel             |
-| ``N``     | Unused or unknown channel |
++-----------+---------------------+
-+-----------+-------------+
+| ``N``     | Unused or unknown   |
+|           | channel             |
++-----------+---------------------+
 
 **Example:**
 - ``"MMNR"``: Indicates four channels: two microphone channels, one unused channel, and one playback reference channel.
@@ -73,6 +75,9 @@ The ``input_format`` parameter specifies the arrangement of audio channels in th
 Using the AFE Framework
 ----------------------------
 
+Based on the ``menuconfig`` -> ``ESP Speech Recognition``, select the required AFE (Analog Front End) models, such as the WakeNet model, VAD (Voice Activity Detection) model, NS (Noise Suppression) model, etc., and then call the AFE framework in the code using the following steps.
+For reference, you can check the code in :project_file:`test_apps/esp-sr/main/test_afe.cpp`.
+
 Step 1: Initialize AFE Configuration
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
@@ -80,6 +85,7 @@ Get the default configuration using ``afe_config_init()`` and customize paramete
 
 .. code-block:: c
 
+    srmodel_list_t *models = esp_srmodel_init("model");
     afe_config_t *afe_config = afe_config_init("MMNR", models, AFE_TYPE_SR, AFE_MODE_HIGH_PERF);
 
 - **``input_format``**: Define the channel arrangement (e.g., ``"MMNR"``).

docs/zh_CN/audio_front_end/README.rst

@@ -53,15 +53,15 @@ AFE 声学前端算法框架
 
 ``input_format`` 参数定义了输入数据中音频通道的排列方式。字符串中的每个字符代表一个通道类型：
 
-+-----------+-------------+
++-----------+---------------------+
-| 字符      | 描述        |
+| 字符      | 描述                |
-+===========+=============+
++===========+=====================+
-| ``M``     | 麦克风通道  |
+| ``M``     | 麦克风通道          |
-+-----------+-------------+
++-----------+---------------------+
-| ``R``     | 播放参考通道 |
+| ``R``     | 播放参考通道        |
-+-----------+-------------+
++-----------+---------------------+
-| ``N``     | 未使用或未知通道 |
+| ``N``     | 未使用或未知通道    |
-+-----------+-------------+
++-----------+---------------------+
 
 **示例：**
 - ``"MMNR"``：表示四通道排列，包含两个麦克风通道、一个未使用通道和一个播放参考通道。
@@ -71,6 +71,8 @@ AFE 声学前端算法框架
 
 使用AFE框架
 ----------------------------
+根据 ``menuconfig`` -> ``ESP Speech Recognition`` 选择需要的AFE的模型，比如WakeNet模型，VAD模型， NS模型等，然后在代码中使用以下步骤调用AFE框架。
+代码可以参考 :project_file:`test_apps/esp-sr/main/test_afe.cpp`。
 
 步骤1：初始化AFE配置
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -79,6 +81,7 @@ AFE 声学前端算法框架
 
 .. code-block:: c
   
+    srmodel_list_t *models = esp_srmodel_init("model");
     afe_config_t *afe_config = afe_config_init("MMNR", models, AFE_TYPE_SR, AFE_MODE_HIGH_PERF);
 
 - **``input_format``**：定义通道排列（如 ``"MMNR"``）。

include/esp32p4/esp_afe_config.h

@@ -110,6 +110,8 @@ typedef struct {
     int vad_min_speech_ms;  // The minimum duration of speech in ms. It should be bigger than 32 ms, default: 128 ms
     int vad_min_noise_ms;   // The minimum duration of noise or silence in ms. It should be bigger than 64 ms, default:
                             // 1000 ms
+    int vad_delay_ms;       // The delay of the first speech frame in ms, default: 128 ms
+                            // If you find vad cache can not cover all speech, please increase this value.
     bool vad_mute_playback; // If true, the playback will be muted for vad detection. default: false
     bool vad_enable_channel_trigger; // If true, the vad will be used to choose the channel id. default: false
 

include/esp32p4/esp_afe_sr_iface.h

@@ -141,12 +141,12 @@ typedef int (*esp_afe_sr_iface_op_reset_buffer_t)(esp_afe_sr_data_t *afe);
 typedef int (*esp_afe_sr_iface_op_set_wakenet_t)(esp_afe_sr_data_t *afe, char *model_name);
 
 /**
- * @brief Enable VAD algorithm.
+ * @brief Reset one function/module/algorithm.
  *
  * @param afe          The AFE_SR object to query
- * @return             -1: fail, 0: disabled, 1: enabled
+ * @return             -1: fail, 1: success
  */
-typedef int (*esp_afe_sr_iface_op_enable_vad_t)(esp_afe_sr_data_t *afe);
+typedef int (*esp_afe_sr_iface_op_reset_op_t)(esp_afe_sr_data_t *afe);
 
 /**
  * @brief Disable one function/module/algorithm.
@@ -204,6 +204,7 @@ typedef struct {
     esp_afe_sr_iface_op_enable_func_t enable_se;
     esp_afe_sr_iface_op_disable_func_t disable_vad;
     esp_afe_sr_iface_op_enable_func_t enable_vad;
+    esp_afe_sr_iface_op_reset_op_t reset_vad;
     esp_afe_sr_iface_op_disable_func_t disable_ns;
     esp_afe_sr_iface_op_enable_func_t enable_ns;
     esp_afe_sr_iface_op_disable_func_t disable_agc;

include/esp32p4/esp_vad.h

@@ -110,7 +110,7 @@ vad_handle_t vad_create(vad_mode_t vad_mode);
  *         - NULL: Create failed
  *         - Others: The instance of VAD
  */
-vad_handle_t vad_create_with_param(vad_mode_t vad_mode, int sample_rate, int one_frame_ms, int min_speech_len, int min_noise_len);
+vad_handle_t vad_create_with_param(vad_mode_t vad_mode, int sample_rate, int one_frame_ms, int min_speech_ms, int min_noise_ms);
 
 /**
  * @brief Feed samples of an audio stream to the VAD and check if there is someone speaking.
@@ -138,6 +138,13 @@ vad_state_t vad_process(vad_handle_t handle, int16_t *data, int sample_rate_hz,
  */
 vad_state_t vad_process_with_trigger(vad_handle_t handle, int16_t *data);
 
+/**
+ * @brief Reset trigger state as Silence
+ *
+ * @param handle            The instance of VAD.
+ */
+void vad_reset_trigger(vad_handle_t handle);
+
 /**
  * @brief Free the VAD instance
  *

include/esp32s3/esp_afe_config.h

@@ -110,6 +110,8 @@ typedef struct {
     int vad_min_speech_ms;  // The minimum duration of speech in ms. It should be bigger than 32 ms, default: 128 ms
     int vad_min_noise_ms;   // The minimum duration of noise or silence in ms. It should be bigger than 64 ms, default:
                             // 1000 ms
+    int vad_delay_ms;       // The delay of the first speech frame in ms, default: 128 ms
+                            // If you find vad cache can not cover all speech, please increase this value.
     bool vad_mute_playback; // If true, the playback will be muted for vad detection. default: false
     bool vad_enable_channel_trigger; // If true, the vad will be used to choose the channel id. default: false
 

include/esp32s3/esp_afe_sr_iface.h

@@ -141,12 +141,12 @@ typedef int (*esp_afe_sr_iface_op_reset_buffer_t)(esp_afe_sr_data_t *afe);
 typedef int (*esp_afe_sr_iface_op_set_wakenet_t)(esp_afe_sr_data_t *afe, char *model_name);
 
 /**
- * @brief Enable VAD algorithm.
+ * @brief Reset one function/module/algorithm.
  *
  * @param afe          The AFE_SR object to query
- * @return             -1: fail, 0: disabled, 1: enabled
+ * @return             -1: fail, 1: success
  */
-typedef int (*esp_afe_sr_iface_op_enable_vad_t)(esp_afe_sr_data_t *afe);
+typedef int (*esp_afe_sr_iface_op_reset_op_t)(esp_afe_sr_data_t *afe);
 
 /**
  * @brief Disable one function/module/algorithm.
@@ -204,6 +204,7 @@ typedef struct {
     esp_afe_sr_iface_op_enable_func_t enable_se;
     esp_afe_sr_iface_op_disable_func_t disable_vad;
     esp_afe_sr_iface_op_enable_func_t enable_vad;
+    esp_afe_sr_iface_op_reset_op_t reset_vad;
     esp_afe_sr_iface_op_disable_func_t disable_ns;
     esp_afe_sr_iface_op_enable_func_t enable_ns;
     esp_afe_sr_iface_op_disable_func_t disable_agc;

include/esp32s3/esp_vad.h

@@ -110,7 +110,7 @@ vad_handle_t vad_create(vad_mode_t vad_mode);
  *         - NULL: Create failed
  *         - Others: The instance of VAD
  */
-vad_handle_t vad_create_with_param(vad_mode_t vad_mode, int sample_rate, int one_frame_ms, int min_speech_len, int min_noise_len);
+vad_handle_t vad_create_with_param(vad_mode_t vad_mode, int sample_rate, int one_frame_ms, int min_speech_ms, int min_noise_ms);
 
 /**
  * @brief Feed samples of an audio stream to the VAD and check if there is someone speaking.
@@ -138,6 +138,13 @@ vad_state_t vad_process(vad_handle_t handle, int16_t *data, int sample_rate_hz,
  */
 vad_state_t vad_process_with_trigger(vad_handle_t handle, int16_t *data);
 
+/**
+ * @brief Reset trigger state as Silence
+ *
+ * @param handle            The instance of VAD.
+ */
+void vad_reset_trigger(vad_handle_t handle);
+
 /**
  * @brief Free the VAD instance
  *