首页|Researchers Submit Patent Application, 'Fast And Efficient Text Only Adaptation For Factorized Neural Transducer', for Approval (USPTO 20240135919)
Researchers Submit Patent Application, 'Fast And Efficient Text Only Adaptation For Factorized Neural Transducer', for Approval (USPTO 20240135919)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News - From Washington, D.C., NewsRx journali sts report that a patent application by the inventors LI, Jinyu (Bellevue, WA, U S); PARTHASARATHY, Sarangarajan (Mountain View, CA, US); XUE, Jian (Bellevue, WA , US); ZHAO, Rui (Bellevue, WA, US), filed on November 9, 2022, was made availab le online on April 25, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information suppli ed by the inventors: “Automatic speech recognition (ASR) systems and other speec h processing systems are used to process and decode audio data to detect speech utterances (e.g., words, phrases, and/or sentences). The processed audio data is then used in various downstream tasks such as search-based queries, speech to t ext transcription, language translation, etc. There are many different types of ASR systems that are being explored. For example, end-to-end (E2E) ASR systems, such as connectionist temporal classification (CTC), attention-based encoder-dec oder, and transducers each work to transfer acoustic features to text sequences. In some instances, the ASR system needs to be adapted for a new domain, in addi tion to being trained in a general baseline domain.
NETL
NSTL
