Google LLC (20240304186). AUDIO SIGNAL SYNTHESIS FROM A NETWORK OF DEVICES simplified abstract
Contents
AUDIO SIGNAL SYNTHESIS FROM A NETWORK OF DEVICES
Organization Name
Inventor(s)
Dongeek Shin of San Jose CA (US)
AUDIO SIGNAL SYNTHESIS FROM A NETWORK OF DEVICES - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240304186 titled 'AUDIO SIGNAL SYNTHESIS FROM A NETWORK OF DEVICES
The abstract describes a patent application for merging first and second audio data to create merged audio data. The first audio data captures a user's spoken utterance and is collected by a computing device in an environment, while the second audio data also captures the same utterance and is collected by a different computing device within the same environment. The merging process involves using weight values based on predicted signal-to-noise ratios (SNRs) for each audio data, determined by processing the audio data using a neural network model.
- The innovation involves merging two sets of audio data collected from different devices to create a single merged audio data.
- Weight values based on predicted SNRs are used to merge the audio data effectively.
- The SNRs are predicted using a neural network model to determine the quality of each audio data.
- This technology aims to improve the overall quality and clarity of the merged audio data.
Potential Applications: - Enhancing voice recognition systems - Improving audio recording quality in noisy environments - Enhancing speech-to-text applications
Problems Solved: - Ensuring better audio quality in merged data - Addressing challenges of collecting audio data from multiple sources - Improving user experience in voice-controlled devices
Benefits: - Enhanced accuracy in speech recognition - Improved user experience in voice-activated devices - Better performance in noisy environments
Commercial Applications: Title: Enhanced Audio Data Merging Technology for Voice Recognition Systems This technology can be applied in various industries such as: - Smart home devices - Virtual assistants - Call center operations
Questions about the technology: 1. How does the use of predicted SNRs improve the merging process of audio data? 2. What are the potential implications of this technology in improving voice recognition systems?
Frequently Updated Research: Stay updated on advancements in neural network models for processing audio data and improving SNR predictions.
Original Abstract Submitted
merging first and second audio data to generate merged audio data, where the first audio data captures a spoken utterance of a user and is collected by a first computing device within an environment, and the second audio data captures the spoken utterance and is collected by a distinct second computing device that is within the environment. in some implementations, the merging includes merging the first audio data using a first weight value and merging the second audio data using a second weight value. the first and second weight values can be based on predicted signal-to-noise ratios (snrs) for respective of the first audio data and the second audio data, such as a first snr predicted by processing the first audio data using a neural network model and a second snr predicted by processing the second audio data using the neural network model.
