Merge pull request #266627 from eric-urban/eur/cnv-updates

American-Dipper · web-flow · commit 1d3271c6b77f · 2024-02-20T19:28:18.000-08:00
cnv training updates
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/create-consent/rest.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/create-consent/rest.md
@@ -1,12 +1,12 @@
 ---
- title: include file
- description: include file
- author: eric-urban
- ms.author: eur
- ms.service: azure-ai-speech
- ms.topic: include
- ms.date: 12/1/2023
- ms.custom: include
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 12/1/2023
+ms.custom: include
 ---
 
 With the professional voice feature, it's required that every voice be created with explicit consent from the user. A recorded statement from the user is required acknowledging that the customer (Azure AI Speech resource owner) will create and use their voice.
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/create-consent/speech-studio.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/create-consent/speech-studio.md
@@ -1,12 +1,12 @@
 ---
- title: include file
- description: include file
- author: eric-urban
- ms.author: eur
- ms.service: azure-ai-speech
- ms.topic: include
- ms.date: 12/1/2023
- ms.custom: include
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 12/1/2023
+ms.custom: include
 ---
 
 A voice talent is an individual or target speaker whose voices are recorded and used to create neural voice models. 
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/create-project/rest.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/create-project/rest.md
@@ -1,12 +1,12 @@
 ---
- title: include file
- description: include file
- author: eric-urban
- ms.author: eur
- ms.service: azure-ai-speech
- ms.topic: include
- ms.date: 12/1/2023
- ms.custom: include
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 12/1/2023
+ms.custom: include
 ---
 
 Professional voice projects contain the voice talent consent statement, training datasets, voice models, and endpoints.
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/create-project/speech-studio.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/create-project/speech-studio.md
@@ -1,12 +1,12 @@
 ---
- title: include file
- description: include file
- author: eric-urban
- ms.author: eur
- ms.service: azure-ai-speech
- ms.topic: include
- ms.date: 12/1/2023
- ms.custom: include
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 12/1/2023
+ms.custom: include
 ---
 
 Content for [Custom neural voice](https://aka.ms/customvoice) like data, models, tests, and endpoints are organized into projects in Speech Studio. Each project is specific to a country/region and language, and the gender of the voice you want to create. For example, you might create a project for a female voice for your call center's chat bots that use English in the United States.
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/create-training-set/rest.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/create-training-set/rest.md
@@ -1,12 +1,12 @@
 ---
- title: include file
- description: include file
- author: eric-urban
- ms.author: eur
- ms.service: azure-ai-speech
- ms.topic: include
- ms.date: 12/1/2023
- ms.custom: include
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 12/1/2023
+ms.custom: include
 ---
 
 You need a training dataset to create a professional voice. A training dataset includes audio and script files. The audio files are recordings of the voice talent reading the script files. The script files are the text of the audio files. 
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/create-training-set/speech-studio.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/create-training-set/speech-studio.md
@@ -1,12 +1,12 @@
 ---
- title: include file
- description: include file
- author: eric-urban
- ms.author: eur
- ms.service: azure-ai-speech
- ms.topic: include
- ms.date: 12/1/2023
- ms.custom: include
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 12/1/2023
+ms.custom: include
 ---
 
 When you're ready to create a custom text to speech voice for your application, the first step is to gather audio recordings and associated scripts to start training the voice model. For details on recording voice samples, see [the tutorial](../../../../record-custom-voice-samples.md). The Speech service uses this data to create a unique voice tuned to match the voice in the recordings. After you've trained the voice, you can start synthesizing speech in your applications.
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/deploy-endpoint/rest.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/deploy-endpoint/rest.md
@@ -1,12 +1,12 @@
 ---
- title: include file
- description: include file
- author: eric-urban
- ms.author: eur
- ms.service: azure-ai-speech
- ms.topic: include
- ms.date: 12/1/2023
- ms.custom: include
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 12/1/2023
+ms.custom: include
 ---
 
 After you've successfully created and [trained](../../../../professional-voice-train-voice.md) your voice model, you deploy it to a custom neural voice endpoint. 
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/deploy-endpoint/speech-studio.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/deploy-endpoint/speech-studio.md
@@ -1,12 +1,12 @@
 ---
- title: include file
- description: include file
- author: eric-urban
- ms.author: eur
- ms.service: azure-ai-speech
- ms.topic: include
- ms.date: 12/1/2023
- ms.custom: include
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 12/1/2023
+ms.custom: include
 ---
 
 After you've successfully created and [trained](../../../../professional-voice-train-voice.md) your voice model, you deploy it to a custom neural voice endpoint. 
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/train-voice/bilingual-training.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/train-voice/bilingual-training.md
@@ -0,0 +1,25 @@
+---
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 2/18/2024
+ms.custom: include
+---
+
+If you select the [Neural](?tabs=neural) training type, you can train a voice to speak in multiple languages. The `zh-CN` and `zh-TW` locales both support bilingual training for the voice to speak both Chinese and English. Depending in part on your training data, the synthesized voice can speak English with an English native accent or English with the same accent as the training data.
+
+> [!NOTE]
+> To enable a voice in the `zh-CN` locale to speak English with the same accent as the sample data, you should choose `Chinese (Mandarin, Simplified), English bilingual` when creating a project or specify the `zh-CN (English bilingual)` locale for the training set data via REST API.
+
+The following table shows the differences between the two locales:
+
+| Speech Studio locale | REST API locale | Bilingual support | 
+|:------------- |:------- |:-------------------------- |
+| `Chinese (Mandarin, Simplified)` | `zh-CN` |If your sample data includes English, the synthesized voice speaks English with an English native accent, instead of the same accent as the sample data, regardless of the amount of English data. | 
+| `Chinese (Mandarin, Simplified), English bilingual` | `zh-CN (English bilingual)` |If you want the synthesized voice to speak English with the same accent as the sample data, we recommend including over 10% English data in your training set. Otherwise, the English speaking accent might not be ideal. |
+| `Chinese (Taiwanese Mandarin, Traditional)` | `zh-TW` | If you want to train a synthesized voice capable of speaking English with the same accent as your sample data, make sure to provide over 10% English data in your training set. Otherwise, it defaults to an English native accent. The 10% threshold is calculated based on the data accepted after successful uploading, not the data before uploading. If some uploaded English data is rejected due to defects and doesn't meet the 10% threshold, the synthesized voice defaults to an English native accent. | 
+
+
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/train-voice/rest.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/train-voice/rest.md
@@ -1,12 +1,12 @@
 ---
- title: include file
- description: include file
- author: eric-urban
- ms.author: eur
- ms.service: azure-ai-speech
- ms.topic: include
- ms.date: 12/1/2023
- ms.custom: include
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 2/18/2024
+ms.custom: include
 ---
 
 
@@ -45,7 +45,7 @@ To create a neural voice, use the [Models_Create](/rest/api/speechapi/models/cre
 - Set the required `projectId` property. See [create a project](../../../../professional-voice-create-project.md).
 - Set the required `consentId` property. See [add voice talent consent](../../../../professional-voice-create-consent.md).
 - Set the required `trainingSetId` property. See [create a training set](../../../../professional-voice-create-training-set.md).
-- Set the required recipe `kind` property to `Default` for neural voice training. The recipe kind indicates the training method and can't be changed later. To use a different training method, see [Neural - cross lingual](?tabs=crosslingual#create-a-voice-model) or [Neural - multi style](?tabs=multistyle#create-a-voice-model).
+- Set the required recipe `kind` property to `Default` for neural voice training. The recipe kind indicates the training method and can't be changed later. To use a different training method, see [Neural - cross lingual](?tabs=crosslingual#create-a-voice-model) or [Neural - multi style](?tabs=multistyle#create-a-voice-model). See [Bilingual training](#bilingual-training) for more information about bilingual training and differences between locales.
 - Set the required `voiceName` property. The voice name must end with "Neural" and can't be changed later. Choose a name carefully. The voice name is used in your [speech synthesis request](../../../../professional-voice-deploy-endpoint.md#use-your-custom-voice) by the SDK and SSML input. Only letters, numbers, and a few punctuation characters are allowed. Use different names for different neural voice models.
 - Optionally, set the `description` property for the voice description. The voice description can be changed later.
 
@@ -227,6 +227,12 @@ You should receive a response body in the following format:
 }
 ```
 
+---
+
+### Bilingual training
+
+[!INCLUDE [Bilingual training](./bilingual-training.md)]
+
 ## Available preset styles across different languages
 
 The following table summarizes the different preset styles according to different languages.
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/train-voice/speech-studio.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/train-voice/speech-studio.md
@@ -5,7 +5,7 @@
  ms.author: eur
  ms.service: azure-ai-speech
  ms.topic: include
- ms.date: 12/1/2023
+ ms.date: 2/18/2024
  ms.custom: include
 ---
 
@@ -47,7 +47,7 @@ To create a custom neural voice in Speech Studio, follow these steps for one of
 
    :::image type="content" source="../../../../media/custom-voice/cnv-train-neural.png" alt-text="Screenshot that shows how to select neural training.":::
 
-1. Select a version of the training recipe for your model. The latest version is selected by default. The supported features and training time can vary by version. Normally, we recommend the latest version. In some cases, you can choose an earlier version to reduce training time.
+1. Select a version of the training recipe for your model. The latest version is selected by default. The supported features and training time can vary by version. Normally, we recommend the latest version. In some cases, you can choose an earlier version to reduce training time. See [Bilingual training](#bilingual-training) for more information about bilingual training and differences between locales.
 1. Select the data that you want to use for training. Duplicate audio names are removed from the training. Make sure that the data you select doesn't contain the same audio names across multiple *.zip* files.
 
    You can select only successfully processed datasets for training. If you don't see your training set in the list, check your data processing status.
@@ -122,6 +122,12 @@ Optionally, you can also select **Add my own test script** and provide your own
 1. Review the settings and select the box to accept the terms of use.
 1. Select **Submit** to start training the model.
 
+---
+
+### Bilingual training
+
+[!INCLUDE [Bilingual training](./bilingual-training.md)]
+
 ## Available preset styles across different languages
 
 The following table summarizes the different preset styles according to different languages.
diff --git a/articles/ai-services/speech-service/includes/how-to/professional-voice/train-voice/voice-styles-by-locale.md b/articles/ai-services/speech-service/includes/how-to/professional-voice/train-voice/voice-styles-by-locale.md
@@ -1,12 +1,12 @@
 ---
- title: include file
- description: include file
- author: eric-urban
- ms.author: eur
- ms.service: azure-ai-speech
- ms.topic: include
- ms.date: 12/1/2023
- ms.custom: include
+title: include file
+description: include file
+author: eric-urban
+ms.author: eur
+ms.service: azure-ai-speech
+ms.topic: include
+ms.date: 2/18/2024
+ms.custom: include
 ---
 
 | Speaking style | Language (locale) |
diff --git a/articles/ai-services/speech-service/professional-voice-train-voice.md b/articles/ai-services/speech-service/professional-voice-train-voice.md
@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/7/2024
+ms.date: 2/18/2024
 ms.author: eur
 zone_pivot_groups: speech-studio-rest
 ---
