Merge pull request #289 from MicrosoftDocs/main

Publish to live, Monday 4 AM PST, 9/16

Author: ttorble

articles/ai-services/.openpublishing.redirection.ai-services.json

@@ -400,6 +400,11 @@
       "redirect_url": "/azure/ai-services/speech-service/quickstarts/setup-platform",
       "redirect_document_id": false
     },
+    {
+      "source_path_from_root": "/articles/ai-services/speech-service/devices-sdk-release-notes.md",
+      "redirect_url": "/azure/ai-services/speech-service/release-notes",
+      "redirect_document_id": false
+    },
     {
       "source_path_from_root": "/articles/ai-services/anomaly-detector/how-to/postman.md",
       "redirect_url": "/azure/ai-services/anomaly-detector/overview",

articles/ai-services/speech-service/custom-neural-voice-lite.md

@@ -6,16 +6,16 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 1/18/2024
+ms.date: 9/15/2024
 ms.author: eur
 ---
 
 # Custom neural voice lite (preview)
 
-Speech Studio provides two custom neural voice (CNV) project types: CNV lite and CNV professional. 
+Azure AI Speech provides two custom neural voice (CNV) project types: CNV lite and CNV professional. 
 
 - Custom neural voice (CNV) professional allows you to upload your training data collected through professional recording studios and create a higher-quality voice that is nearly indistinguishable from its human samples. CNV professional access is limited based on eligibility and usage criteria. Request access on the [intake form](https://aka.ms/customneural).
-- Custom neural voice (CNV) lite is a project type in public preview. You can demo and evaluate custom neural voice before investing in professional recordings to create a higher-quality voice. No application is required. Microsoft restricts and selects the recording and testing samples for use with CNV lite. You must apply for full access to CNV professional in order to deploy and use the CNV lite model for business purpose. 
+- Custom neural voice (CNV) lite is a project type in public preview. You can demo and evaluate custom neural voice before investing in professional recordings to create a higher-quality voice. No application is required for demo and evaluation purposes. However, Microsoft restricts and selects the recording and testing samples for use with CNV lite. You must apply for full access to CNV professional in order to deploy and use the CNV lite model for business purpose. In that case, request access on the [intake form](https://aka.ms/customneural).
 
 With a CNV lite project, you record your voice online by reading 20-50 pre-defined scripts provided by Microsoft. After you've recorded at least 20 samples, you can start to train a model. Once the model is trained successfully, you can review the model and check out 20 output samples produced with another set of pre-defined scripts.
 
@@ -41,27 +41,27 @@ The following table summarizes key differences between the CNV lite and CNV prof
 To create a custom neural voice lite project, follow these steps:
 
 1. Sign in to the [Speech Studio](https://aka.ms/speechstudio/customvoice).
-1. Select the subscription and Speech resource to work with. 
-
-    > [!IMPORTANT]
-    > Custom neural voice training is currently only available in some regions. See footnotes in the [regions](regions.md#speech-service) table for more information.
-
+1. Select the subscription and Speech resource to work with.
 1. Select **Custom voice** > **Create a project**. 
-1. Select **Custom neural voice lite** > **Next**. 
-
-    > [!NOTE]
-    > To create a custom neural voice Pro project, see [Create a project for custom neural voice](professional-voice-create-project.md).
+1. Select **Custom neural voice lite** > **Next**. To create a custom neural voice professional project instead, see [Create a project for custom neural voice](professional-voice-create-project.md).
 
 1. Follow the instructions provided by the wizard to create your project. 
+    
+    > [!IMPORTANT]
+    > The CNV lite project expires after 90 days unless the [verbal statement](#submit-verbal-statement) recorded by the voice talent is submitted.
+
 1. Select the new project by name or select **Go to project**. You see these menu items in the left panel: **Record and build**, **Review model**, and **Deploy model**.  
+
     :::image type="content" source="media/custom-voice/lite/lite-project-get-started.png" alt-text="Screenshot with an overview of the CNV lite record, train, test, and deploy workflow.":::
 
-The CNV lite project expires after 90 days unless the [verbal statement](#submit-verbal-statement) recorded by the voice talent is submitted.
 
 ## Record and build a CNV lite model
 
 Record at least 20 voice samples (up to 50) with provided scripts online. Voice samples recorded here are used to create a synthetic version of your voice.
 
+> [!NOTE]
+> Custom neural voice training is currently only available in some regions. See footnotes in the [regions](regions.md#speech-service) table for more information.
+
 Here are some tips to help you record your voice samples:
 - Use a good microphone. Increase the clarity of your samples by using a high-quality microphone. Speak about 8 inches away from the microphone to avoid mouth noises.
 - Avoid background noise. Record in a quiet room without background noise or echoing.

articles/ai-services/speech-service/custom-neural-voice.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: conceptual
-ms.date: 1/18/2024
+ms.date: 9/15/2024
 ms.author: eur
 ---
 
@@ -49,8 +49,6 @@ Here's an overview of the steps to create a custom neural voice in Speech Studio
 You can tune, adjust, and use your custom voice, similarly as you would use a prebuilt neural voice. Convert text into speech in real-time, or generate audio content offline with text input. You use the [REST API](./rest-text-to-speech.md), the [Speech SDK](./get-started-text-to-speech.md), or the [Speech Studio](https://speech.microsoft.com/audiocontentcreation).
 
 > [!TIP]
-> You can also use the Speech SDK and custom voice REST API to train a custom neural voice.
-> 
 > Check out the code samples in the [Speech SDK repository on GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/samples/custom-voice/README.md) to see how to use custom neural voice in your application.
 
 The style and the characteristics of the trained voice model depend on the style and the quality of the recordings from the voice talent used for training. However, you can make several adjustments by using [SSML (Speech Synthesis Markup Language)](./speech-synthesis-markup.md?tabs=csharp) when you make the API calls to your voice model to generate synthetic speech. SSML is the markup language used to communicate with the text to speech service to convert text into audio. The adjustments you can make include change of pitch, rate, intonation, and pronunciation correction. If the voice model is built with multiple styles, you can also use SSML to switch the styles.
@@ -67,10 +65,6 @@ Next, the phoneme sequence goes into the neural acoustic model to predict acoust
 Neural text to speech voice models are trained by using deep neural networks based on
 the recording samples of human voices. For more information, see [this Microsoft blog post](https://techcommunity.microsoft.com/t5/azure-ai/neural-text-to-speech-extends-support-to-15-more-languages-with/ba-p/1505911). To learn more about how a neural vocoder is trained, see [this Microsoft blog post](https://techcommunity.microsoft.com/t5/azure-ai/azure-neural-tts-upgraded-with-hifinet-achieving-higher-audio/ba-p/1847860).
 
-## Migrate to custom neural voice
-
-If you're using the old version of custom voice (which is scheduled to be retired in February 2024), see [How to migrate to custom neural voice](how-to-migrate-to-custom-neural-voice.md).
-
 ## Responsible AI 
 
 An AI system includes not only the technology, but also the people who use it, the people who are affected by it, and the environment in which it's deployed. Read the transparency notes to learn about responsible AI use and deployment in your systems. 

articles/ai-services/speech-service/custom-speech-overview.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: overview
-ms.date: 1/19/2024
+ms.date: 9/15/2024
 ms.author: eur
 ms.custom: references_regions
 ---
@@ -35,7 +35,7 @@ Here's more information about the sequence of steps shown in the previous diagra
 1. [Test model quantitatively](how-to-custom-speech-evaluate-data.md). Evaluate and improve the accuracy of the speech to text model. The Speech service provides a quantitative word error rate (WER), which you can use to determine if more training is required. 
 1. [Train a model](how-to-custom-speech-train-model.md). Provide written transcripts and related text, along with the corresponding audio data. Testing a model before and after training is optional but recommended.
     > [!NOTE]
-    > You pay for custom speech model usage and [endpoint hosting](how-to-custom-speech-deploy-model.md). You'll also be charged for custom speech model training if the base model was created on October 1, 2023 and later. You are not charged for training if the base model was created prior to October 2023. For more information, see  [Azure AI Speech pricing](https://azure.microsoft.com/pricing/details/cognitive-services/speech-services/) and the [Charge for adaptation section in the speech to text 3.2 migration guide](./migrate-v3-1-to-v3-2.md#charge-for-adaptation).
+    > You pay for custom speech model usage and [endpoint hosting](how-to-custom-speech-deploy-model.md). You'll also be charged for custom speech model training if the base model was created on October 1, 2023 and later. You're not charged for training if the base model was created prior to October 2023. For more information, see [Azure AI Speech pricing](https://azure.microsoft.com/pricing/details/cognitive-services/speech-services/) and the [Charge for adaptation section in the speech to text 3.2 migration guide](./migrate-v3-1-to-v3-2.md#charge-for-adaptation).
 1. [Deploy a model](how-to-custom-speech-deploy-model.md). Once you're satisfied with the test results, deploy the model to a custom endpoint. Except for [batch transcription](batch-transcription.md), you must deploy a custom endpoint to use a custom speech model.
     > [!TIP]
     > A hosted deployment endpoint isn't required to use custom speech with the [Batch transcription API](batch-transcription.md). You can conserve resources if the custom speech model is only used for batch transcription. For more information, see [Speech service pricing](https://azure.microsoft.com/pricing/details/cognitive-services/speech-services/).

articles/ai-services/speech-service/customize-pronunciation.md

@@ -5,7 +5,7 @@ author: ut-karsh
 ms.author: umaheshwari
 ms.service: azure-ai-speech
 ms.topic: conceptual
-ms.date: 1/18/2024
+ms.date: 9/15/2024
 ms.custom: template-concept
 ---
 

articles/ai-services/speech-service/devices-sdk-release-notes.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: overview
-ms.date: 1/18/2024
+ms.date: 9/15/2024
 ms.author: eur
 ms.custom: cogserv-non-critical-speech
 ---
@@ -53,10 +53,6 @@ Voice assistants built using Speech service can use the full range of customizat
 
 Direct Line Speech and its associated functionality for voice assistants are an ideal supplement to the [Virtual Assistant Solution and Enterprise Template](/azure/bot-service/bot-builder-enterprise-template-overview). Though Direct Line Speech can work with any compatible bot, these resources provide a reusable baseline for high-quality conversational experiences and common supporting skills and models to get started quickly.
 
-## Reference docs
-
-* [Speech SDK](./speech-sdk.md)
-* [Azure AI Bot Service](/azure/bot-service/)
 
 ## Next steps
 

articles/ai-services/speech-service/direct-line-speech.md

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-speech
 ms.custom: devx-track-extended-java, devx-track-go, devx-track-js, devx-track-python
 ms.topic: conceptual
-ms.date: 1/18/2024
+ms.date: 9/15/2024
 ms.author: eur
 zone_pivot_groups: programming-languages-speech-sdk-cli
 ---
@@ -172,8 +172,7 @@ spx recognize --file caption.this.mp4 --format any --profanity masked --output v
 
 Profanity filter is applied to the result `Text` and `MaskedNormalizedForm` properties. Profanity filter isn't applied to the result `LexicalForm` and `NormalizedForm` properties. Neither is the filter applied to the word level results.
 
-
-## Next steps
+## Related content
 
 * [Speech to text quickstart](get-started-speech-to-text.md)
 * [Get speech recognition results](get-speech-recognition-results.md)