SAMSUNG ELECTRONICS CO., LTD. (20240339123). SYSTEM AND METHOD FOR KEYWORD SPOTTING IN NOISY ENVIRONMENTS simplified abstract

SYSTEM AND METHOD FOR KEYWORD SPOTTING IN NOISY ENVIRONMENTS

Organization Name

SAMSUNG ELECTRONICS CO., LTD.

Inventor(s)

Chou-Chang Yang of San Jose CA (US)

Yashas Malur Saidutta of Menlo Park CA (US)

Rakshith Sharma Srinivasa of Sunnyvale CA (US)

Ching-Hua Lee of Mountain View CA (US)

Yilin Shen of San Jose CA (US)

Hongxia Jin of San Jose CA (US)

SYSTEM AND METHOD FOR KEYWORD SPOTTING IN NOISY ENVIRONMENTS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240339123 titled 'SYSTEM AND METHOD FOR KEYWORD SPOTTING IN NOISY ENVIRONMENTS

Simplified Explanation: The patent application describes a method that processes audio input to detect the presence of speech and keywords, enhancing the audio quality for better keyword classification.

Key Features and Innovation:

• Receiving audio input and generating a noisy time-frequency representation.
• Providing the representation to a noise management model to predict denoising mask and signal presence probability.
• Determining an enhanced spectrogram using the denoising mask.
• Providing the enhanced spectrogram and signal presence probability map to a keyword classification model.
• Transmitting audio input to a downstream application if a keyword is detected.

Potential Applications: This technology can be used in speech recognition systems, voice-controlled devices, and keyword-based audio search applications.

Problems Solved: The method addresses the challenges of noise interference in audio signals, improving the accuracy of speech and keyword detection in noisy environments.

Benefits:

• Enhanced audio quality for better speech and keyword recognition.
• Improved performance of keyword classification models.
• Increased efficiency in processing audio data in noisy conditions.

Commercial Applications: The technology can be applied in virtual assistants, smart speakers, call center analytics, and audio transcription services to enhance user experience and accuracy in keyword detection.

Prior Art: Researchers can explore prior art related to audio signal processing, speech recognition, and keyword detection algorithms to understand the evolution of similar technologies.

Frequently Updated Research: Stay updated on advancements in noise reduction techniques, machine learning models for audio processing, and keyword detection algorithms to enhance the performance of the described method.

Questions about Audio Signal Processing: 1. How does the method differentiate between speech and background noise in the audio input? 2. What are the key factors influencing the accuracy of keyword classification in noisy environments?

Original Abstract Submitted

a method includes receiving an audio input and generating a noisy time-frequency representation based on the audio input. the method also includes providing the noisy time-frequency representation to a noise management model trained to predict a denoising mask and a signal presence probability (spp) map indicating a likelihood of a presence of speech. the method further includes determining an enhanced spectrogram using the denoising mask and the noisy time-frequency representation. the method also includes providing the enhanced spectrogram and the spp map as inputs to a keyword classification model trained to determine a likelihood of a keyword being present in the audio input. in addition, the method includes, responsive to determining that a keyword is in the audio input, transmitting the audio input to a downstream application associated with the keyword.