feat(tts): Updata TTS and xiaoxin voice data

This commit is contained in:
sxy 2022-07-27 20:20:52 +08:00
parent bbbe7849cd
commit 1412145066
5 changed files with 14 additions and 14 deletions

View File

@ -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.

View File

@ -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。