NVIDIA had 235 patents in artificial intelligence during Q4 2023. NVIDIA Corp’s Q4 2023 patents include methods for generating synthetic speech with sampled phoneme durations and additional information, systems for detecting inefficiencies in workloads by comparing information to inefficiency patterns, tools for modifying HD map data with synthetic objects and generating synthetic sensor data, a robot device for resolving errors in a data center environment through candidate maintenance operations, and algorithms for photorealistic image synthesis using low discrepancy sequences to reduce noise and improve efficiency in sampling light transport paths. GlobalData’s report on NVIDIA gives a 360-degreee view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
NVIDIA grant share with artificial intelligence as a theme is 31% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Unsupervised alignment for text to speech synthesis using neural networks (Patent ID: US20230419947A1)
The patent filed by NVIDIA Corp. describes a computer-implemented method for generating synthetic speech from an input text sequence by determining phoneme distributions, pitch distributions, and energy distributions from audio segments. The method involves aligning text sequences with speech durations, sampling phoneme durations, and generating speech alignments for audio segments based on these distributions. The synthesized audio recitation is then generated based on the speech alignment, providing improved diversity in synthetic speech generation.
Furthermore, the system and processor described in the patent utilize parallel processing units to generate synthetic audio segments based on phoneme distributions, pitch, and energy distributions. The system fits beta-binomial distributions to the synthetic alignment, applies specified ranges for probabilities, and generates synthetic recitations that are generative and unique for each sequence of text. The processor determines alignments between text and audio samples, extracts speaker characteristics, and generates synthetic audio clips from input text sequences based on vectors derived from the alignment distribution. The alignment distribution is based on an alignment matrix with a beta-binomial distribution, enhancing the accuracy and diversity of the synthetic speech generation process.
To know more about GlobalData’s detailed insights on NVIDIA, 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.
