20240038278. METHOD AND DEVICE FOR TIMING ALIGNMENT OF AUDIO SIGNALS simplified abstract (GOERTEK INC.)

From WikiPatents
Jump to navigation Jump to search

METHOD AND DEVICE FOR TIMING ALIGNMENT OF AUDIO SIGNALS

Organization Name

GOERTEK INC.

Inventor(s)

LIBING Zou of Weifang, Shandong (CN)

Yifan Zhang of Weifang, Shandong (CN)

Xueqiang Wang of Weifang, Shandong (CN)

Fuqiang Zhang of Weifang, Shandong (CN)

METHOD AND DEVICE FOR TIMING ALIGNMENT OF AUDIO SIGNALS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240038278 titled 'METHOD AND DEVICE FOR TIMING ALIGNMENT OF AUDIO SIGNALS

Simplified Explanation

The patent application describes a method and device for timing alignment of audio signals using deep neural networks. Here is a simplified explanation of the abstract:

  • The method involves generating frequency domain images for an audio signal to be aligned and a template audio signal.
  • These frequency domain images are inputted into a twin neural network of a timing offset prediction model to obtain two frequency domain features.
  • The two frequency domain features are fused to obtain a fused feature.
  • The fused feature is then inputted into a prediction network of the timing offset prediction model to obtain a timing offset output.
  • Finally, timing alignment processing is performed on the audio signal to be aligned based on the timing offset.

Potential applications of this technology:

  • Audio signal processing and synchronization in various industries such as broadcasting, telecommunications, and multimedia production.
  • Real-time audio alignment in live performances or events where multiple audio sources need to be synchronized.

Problems solved by this technology:

  • Accurate and robust timing alignment of audio signals, even in noisy environments.
  • Extraction of more intrinsic and stable features using deep neural networks.

Benefits of this technology:

  • More accurate and faster timing offset prediction compared to traditional methods.
  • Improved synchronization of audio signals, leading to better audio quality and user experience.


Original Abstract Submitted

a method and device for timing alignment of audio signals. the method includes: generating frequency domain images respectively for an audio signal to be aligned and a template audio signal (s); inputting the frequency domain images into a twin neural network of a timing offset prediction model respectively, to obtain two frequency domain features output by the twin neural network (s); fusing the two frequency domain features to obtain a fused feature (s); inputting the fused features into a prediction network of the timing offset prediction model to obtain a timing offset output by the prediction network (s); and performing timing alignment processing on the audio signal to be aligned according to the timing offset (s). the technical solution is more robust, and especially in a noisy environment, features extracted by a deep neural network are more intrinsic and more stable. an end-to-end timing offset prediction model is more accurate and faster.

Retrieved from "http://wikipatents.org/index.php?title=20240038278._METHOD_AND_DEVICE_FOR_TIMING_ALIGNMENT_OF_AUDIO_SIGNALS_simplified_abstract_(GOERTEK_INC.)&oldid=30379"