Nvidia patents speech recognition method that skips silent audio frames
Nvidia describes a method for training speech recognition software to ignore specific parts of audio input without penalizing the model's accuracy. The system uses a mathematical framework to skip frames that contain no useful speech, simplifying the training process and making the code easier to debug.
In the filing’s own words
Systems and methods provide for a machine learning system to train a machine learning model to output a penalty-free emission when processing an auditory input. For example, as the system generates paths through a probability lattice, one or more paths may include a penalty-free emission that skips at least one frame associated with the probability lattice, but that does not add a cost to a final path cost. The use of the penalty-free emissions may be represented through one or more graphical representations used for training in order to develop loss functions for models. One or more of these frameworks may be incorporated into automatic speech recognition pipelines to improve training while also reducing coding requirements to simplify debugging operations.
What exactly they claim (claim 1)
1. A processor comprising: one or more circuits configured to perform, using a neural network (NN), one or more automatic speech recognition (ASR) operations with respect to a sequence of audio frames, the operations using at least a three-dimensional (3D) tensor converted from a four-dimensional (4D) tensor by combination of an audio dimension and a text dimension, the one or more circuits configured to, responsive to an output of the NN indicating an emulated blank for at least one audio frame of the sequence of audio frames, omit at least one audio frame from processing without affecting a loss score.
Facts
- Company
- Nvidia (Nvidia Corporation)
- Official title
- Weighted finite state transducer frameworks for conversational AI systems and applications
- Patent number
- US12731577B2
- Application number
- 18355646
- Filed
- Jul 20, 2023
- Granted
- Sep 8, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G10L 15/16 Physics & computingG10L 15/063 Physics & computingG10L 15/22 Physics & computingMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents AI method to make digital characters move realistically Sep 8, 2026
- Nvidia patents AI system that builds image generators from text prompts Sep 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.