mirror of
https://github.com/espressif/esp-sr.git
synced 2025-09-15 15:28:44 +08:00
feat(tts): Updata TTS and xiaoxin voice data
This commit is contained in:
parent
bbbe7849cd
commit
1412145066
@ -37,7 +37,7 @@ The workflow is as follows:
|
||||
|
||||
The workflow is as follows:
|
||||
|
||||
1) Use **ESP_AFE_VOIP_HANDLE** to create and initialize AFE (`voice_communication_init` needs to be configured as true)
|
||||
1) Use **ESP_AFE_VC_HANDLE** to create and initialize AFE (`voice_communication_init` needs to be configured as true)
|
||||
2) AFE feed: Input audio data and will run AEC in the feed function
|
||||
3) Internal: BSS/NS algorithm processing will be carried out. If it's dual MIC, the miso algorithm processing will be carried out later.
|
||||
4) AFE fetch: Return the audio data and the related information after processing. The AGC algorithm processing will be carried out. And the specific gain depends on the config of `afe_config_t` structure. If it's dual MIC, the NS algorithm processing will be carried out before AGC.(Note: `wakenet_Init` and `voice_communication_Init` cannot be configured to true at the same time)
|
||||
@ -60,7 +60,7 @@ For the acquisition of AFE handle, there is a slight difference between speech r
|
||||
|
||||
- Voice communication
|
||||
|
||||
esp_afe_sr_iface_t *afe_handle = &ESP_AFE_VOIP_HANDLE;
|
||||
esp_afe_sr_iface_t *afe_handle = &ESP_AFE_VC_HANDLE;
|
||||
|
||||
### Input Audio data
|
||||
|
||||
@ -141,7 +141,7 @@ The output audio of AFE is single-channel data. In the speech recognition scenar
|
||||
|
||||
- Voice communication
|
||||
|
||||
esp_afe_sr_iface_t *afe_handle = &ESP_AFE_VOIP_HANDLE;
|
||||
esp_afe_sr_iface_t *afe_handle = &ESP_AFE_VC_HANDLE;
|
||||
|
||||
### 2. Configure AFE
|
||||
|
||||
@ -158,8 +158,8 @@ Users can adjust the switch of each algorithm module and its corresponding param
|
||||
.vad_init = true, \
|
||||
.wakenet_init = true, \
|
||||
.voice_communication_init = false, \
|
||||
.voip_agc_init = false, \
|
||||
.voip_agc_gain = 15, \
|
||||
.voice_communication_agc_init = false, \
|
||||
.voice_communication_agc_gain = 15, \
|
||||
.vad_mode = VAD_MODE_3, \
|
||||
.wakenet_model_name = NULL, \
|
||||
.wakenet_mode = DET_MODE_2CH_90, \
|
||||
@ -185,9 +185,9 @@ Users can adjust the switch of each algorithm module and its corresponding param
|
||||
|
||||
- voice_communication_init: Whether voice communication is enabled. It cannot be enabled with wakenet_init at the same time.
|
||||
|
||||
- voip_agc_init: Whether the AGC is enabled in voice communication.
|
||||
- voice_communication_agc_init: Whether the AGC is enabled in voice communication.
|
||||
|
||||
- voip_agc_gain: The gain of AGC ( unit: dB )
|
||||
- voice_communication_agc_gain: The gain of AGC ( unit: dB )
|
||||
|
||||
- vad_mode: The VAD operating mode. The bigger, the more radical.
|
||||
|
||||
|
||||
@ -37,7 +37,7 @@
|
||||
|
||||
工作流程如下:
|
||||
|
||||
1) 使用 **ESP_AFE_VOIP_HANDLE**,进行AFE 的创建和初始化 (`voice_communication_init`需配置为 true )
|
||||
1) 使用 **ESP_AFE_VC_HANDLE**,进行AFE 的创建和初始化 (`voice_communication_init`需配置为 true )
|
||||
2) AFE feed,输入音频数据,feed 内部会先进行 AEC 算法处理
|
||||
3) 内部: 首先进行 BSS/NS 算法处理;若为双麦,随后还会进行MISO 算法处理;
|
||||
4) AFE fetch,返回处理过的单通道音频数据和相关信息。其中会进行AGC非线性放大,具体增益值取决于用户对 `afe_config_t` 结构体的配置;若为双麦,在AGC之前还会进行降噪处理。(注:`wakenet_init` 和 `voice_communication_init` 不可同时配置为 true)
|
||||
@ -60,7 +60,7 @@
|
||||
|
||||
- 语音通话
|
||||
|
||||
esp_afe_sr_iface_t *afe_handle = &ESP_AFE_VOIP_HANDLE;
|
||||
esp_afe_sr_iface_t *afe_handle = &ESP_AFE_VC_HANDLE;
|
||||
|
||||
### 输入音频
|
||||
|
||||
@ -141,7 +141,7 @@ AFE 的输出音频为单通道数据。在语音识别场景,若WakeNet 开
|
||||
|
||||
- 语音通话
|
||||
|
||||
esp_afe_sr_iface_t *afe_handle = &ESP_AFE_VOIP_HANDLE;
|
||||
esp_afe_sr_iface_t *afe_handle = &ESP_AFE_VC_HANDLE;
|
||||
|
||||
### 2. 配置 afe
|
||||
|
||||
@ -158,8 +158,8 @@ AFE 的输出音频为单通道数据。在语音识别场景,若WakeNet 开
|
||||
.vad_init = true, \
|
||||
.wakenet_init = true, \
|
||||
.voice_communication_init = false, \
|
||||
.voip_agc_init = false, \
|
||||
.voip_agc_gain = 15, \
|
||||
.voice_communication_agc_init = false, \
|
||||
.voice_communication_agc_gain = 15, \
|
||||
.vad_mode = VAD_MODE_3, \
|
||||
.wakenet_model_name = NULL, \
|
||||
.wakenet_mode = DET_MODE_2CH_90, \
|
||||
@ -185,9 +185,9 @@ AFE 的输出音频为单通道数据。在语音识别场景,若WakeNet 开
|
||||
|
||||
- voice_communication_init: 语音通话是否使能。与 wakenet_init 不能同时使能。
|
||||
|
||||
- voip_agc_init: 语音通话中AGC是否使能。
|
||||
- voice_communication_agc_init: 语音通话中AGC是否使能。
|
||||
|
||||
- voip_agc_gain: AGC的增益值,单位为dB。
|
||||
- voice_communication_agc_gain: AGC的增益值,单位为dB。
|
||||
|
||||
- vad_mode: VAD 检测的操作模式,越大越激进。
|
||||
|
||||
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Loading…
Reference in New Issue
Block a user