![]() This diagram covers three different types of processing: how Microsoft verifies voice files of the voice talent prior to the custom neural voice model training, how Microsoft creates a custom neural voice model with your training data, and how TTS processes your text input to generate audio content. The diagram below illustrates how your data is processed. How does Custom Neural Voice and TTS process data? This is the text you select and send to TTS to generate audio content using your custom neural voice. You can upload your own text-based scripts to evaluate and test the quality of the custom voice model by generating speech synthesis audio samples. Both the audio recordings and the text transcription files will be used as the voice model Training Data. You can provide their own text transcriptions of audio or use the automated speech recognition transcription feature available within the Speech Studio to generate a text transcription of the audio. This includes audio recordings from the voice talent who has agreed to use his/her voice for the model training and the related text transcripts. Training data (including audio files and related text transcripts). “I am aware that recordings of my voice will be used by to create and use a synthetic version of my voice.”ĭifferent versions of the copy are provided based on the language you select to create Custom Neural Voice for. When preparing your recording script, make sure you include the below sentence to acquire the voice talent acknowledgement. When using the Speech Studio, customers are required to upload a recorded statement of the voice talent that acknowledges that his/her voice will be used by customer to create synthetic voice(s). What data does Custom Neural Voice and TTS process?Ĭustom Neural Voice processes the following types of data: Before using Custom Neural Voice and the TTS service for the processing and storage of data and creation of synthetic speech, you must ensure compliance with any such legal requirements that may apply to you. Some jurisdictions may impose special legal requirements for the collection, processing and storage of certain categories of data, such as biometric data and mandate disclosing the use of synthetic voices to users. As an important reminder, you are responsible for your use and the implementation of this technology and are required to obtain all necessary permissions from voice talents for the processing of his/her voice data to develop a synthetic voice as well as any licenses, permissions or other proprietary rights required for the content you input into the text-to-speech (“TTS”) service, part of Speech in Azure Cognitive Services, to generate audio content in the synthetic voice. ![]() ![]() This article provides details regarding how Custom Neural Voice data provided by you is processed, used and stored.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |