SAS Institute has patented a system using machine learning to correct audio transcriptions in speech-to-text services. The technology involves training data samples, model configuration, and post-processing sequences to improve accuracy. The method aims to enhance transcription quality for better user experience. GlobalData’s report on SAS Institute gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on SAS Institute, Facial recognition AI was a key innovation area identified from patents. SAS Institute's grant share as of February 2024 was 82%. Grant share is based on the ratio of number of grants to total number of patents.
Audio transcript correction machine learning model for speech-to-text service
A recently granted patent (Publication Number: US11922947B2) discloses a computer-program product stored in a non-transitory machine-readable storage medium that aims to improve audio transcription accuracy through machine learning. The product includes operations such as constructing a training data corpus with labeled audio transcription samples, configuring a machine learning model, and adapting the model based on anomalous data. The model is then used to correct transcription errors in predicted audio transcripts, enhancing the overall accuracy of speech-to-text services. The system also involves generating task-specific instructions for the model to identify and correct errors, ensuring a minimum level of transcription efficacy.
Furthermore, the patent details a method and system for implementing the described technology, involving processors, memory, and computer-readable instructions. The system is designed to construct training data, train machine learning models, and execute them within speech-to-text services to enhance transcription accuracy. By generating corrected audio transcripts based on predicted transcripts, the system aims to improve the quality of transcribed audio data. Additionally, the system includes features such as identifying task types, utilizing weights and biases for adjustments, and ensuring a minimum level of accuracy for corrected transcripts. Overall, the technology outlined in the patent focuses on leveraging machine learning to enhance the accuracy and efficiency of audio transcription processes within speech-to-text services.
To know more about GlobalData’s detailed insights on SAS Institute, buy the report here.
Premium Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
