Amazon Transcribe improves live subtitling with partial results stabilization
We are excited to announce that Amazon Transcribe now supports partial results stabilization, which further improves the live subtitling experience. Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for you to add speech-to-text capabilities to your applications. As Amazon Transcribe processes streaming audio content, it generates partial transcription results until it provides a final transcript for a segment of continuous speech. However, some words or phrases in these partial results might change as Transcribe further understands the context of the audio. Partial results stabilization makes it easier for viewers to read the text output by defining how much the transcript will change during the transcription process.
We are excited to announce that Amazon Transcribe now supports partial results stabilization, which further improves the live subtitling experience. Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for you to add speech-to-text capabilities to your applications. As Amazon Transcribe processes streaming audio content, it generates partial transcription results until it provides a final transcript for a segment of continuous speech. However, some words or phrases in these partial results might change as Transcribe further understands the context of the audio. Partial results stabilization makes it easier for viewers to read the text output by defining how much the transcript will change during the transcription process.
Instead of waiting for an entire sentence to be transcribed, you can now control the stabilization level of partial results. Transcribe offers 3 settings: High, Medium and Low. Setting the stabilization “High” allows a greater portion of the partial results to be fixed with only the last few words changing during the transcription process. This enables you to present transcription results to your viewers in smaller segments that do not exceed two lines of subtitling on the screen at one time. In addition, partial results stabilization improves the user experience and reduces latency.
Partial results stabilization can improve the live subtitling experience for video broadcasts and in-game chats. For example, media customers can use Transcribe to make their live sports events accessible with real-time subtitles and can use partial results stabilization to lower latency. Video game companies can also use streaming transcription to improve accessibility for in-game chat, helping players who have hearing impairments. Contact centers can use this streaming transcription capability to transcribe calls in real-time for agents to trigger the next best actions.
Partial results stabilization is now available for streaming audio in all AWS regions where Amazon Transcribe is available. To get started, read “Improve the streaming transcription experience with Amazon Transcribe partial results stabilization” post and try it out on the Amazon Transcribe service console. For more information, visit the Amazon Transcribe partial results stabilization documentation.