Google llc (20240203438). NOISE SUPPRESSION FOR SPEECH DATA WITH REDUCED POWER CONSUMPTION simplified abstract
Contents
NOISE SUPPRESSION FOR SPEECH DATA WITH REDUCED POWER CONSUMPTION
Organization Name
Inventor(s)
Chandan Karadagur Ananda Reddy of Cupertino CA (US)
Navin Chatlani of Palo Alto CA (US)
NOISE SUPPRESSION FOR SPEECH DATA WITH REDUCED POWER CONSUMPTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240203438 titled 'NOISE SUPPRESSION FOR SPEECH DATA WITH REDUCED POWER CONSUMPTION
The patent application describes a method for providing noise suppression for speech data with reduced power consumption.
- Receiving a current time frame of speech data and transforming it into a current frequency frame in the frequency domain.
- Using a noise classifier to determine whether to create a current noise suppression mask for the current frame.
- Creating the mask and multiplying it by the current frequency frame to obtain a noise-suppressed frequency frame if necessary.
- Multiplying the previous noise suppression mask with the current frequency frame to obtain the noise-suppressed frequency frame if a new mask is not needed.
- Transforming the noise-suppressed frequency frame back to a time frame and outputting the result.
Potential Applications: - Telecommunications - Speech recognition systems - Audio processing software
Problems Solved: - Reducing power consumption in noise suppression for speech data - Improving speech quality in noisy environments
Benefits: - Enhanced speech clarity - Lower power consumption - Improved user experience in speech-related applications
Commercial Applications: Title: "Efficient Noise Suppression Technology for Speech Data" This technology can be used in mobile phones, voice-controlled devices, and audio recording equipment to enhance speech quality and reduce power consumption.
Questions about Noise Suppression Technology: 1. How does this technology compare to traditional noise suppression methods? This technology offers improved efficiency and reduced power consumption compared to traditional methods by dynamically creating noise suppression masks only when necessary.
2. What impact does this technology have on speech recognition accuracy? By reducing background noise in speech data, this technology can improve speech recognition accuracy in noisy environments.
Original Abstract Submitted
implementations described herein relate to providing noise suppression for speech data with reduced power consumption. in some implementations, a computer-implemented method includes receiving a current time frame of speech data, e.g., after receiving a previous time frame associated with a previous noise suppression mask. the current time frame is transformed to a current frequency frame in the frequency domain. a noise classifier is used to determine whether to create a current noise suppression mask for the current frame. if it is determined to create the mask, the mask is created and multiplied by the current frequency frame to obtain a noise-suppressed frequency frame. if it is determined to not create the current mask, the previous noise suppression mask is multiplied with the current frequency frame to obtain the noise-suppressed frequency frame, without creating a mask. the noise-suppressed frequency frame is transformed to a time frame and output.
