17988376. TRANSFORMING SPEECH SIGNALS TO ATTENUATE SPEECH OF COMPETING INDIVIDUALS AND OTHER NOISE simplified abstract (Cisco Technology, Inc.)
Contents
- 1 TRANSFORMING SPEECH SIGNALS TO ATTENUATE SPEECH OF COMPETING INDIVIDUALS AND OTHER NOISE
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 TRANSFORMING SPEECH SIGNALS TO ATTENUATE SPEECH OF COMPETING INDIVIDUALS AND OTHER NOISE - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
TRANSFORMING SPEECH SIGNALS TO ATTENUATE SPEECH OF COMPETING INDIVIDUALS AND OTHER NOISE
Organization Name
Inventor(s)
Kamil Krzysztof Wojcicki of Kangaroo Point (AU)
Xuehong Mao of San Jose CA (US)
David Guoqing Zhang of Fremont CA (US)
Samer Hijazi of San Jose CA (US)
Raul Alejandro Casas of Doylestown PA (US)
TRANSFORMING SPEECH SIGNALS TO ATTENUATE SPEECH OF COMPETING INDIVIDUALS AND OTHER NOISE - A simplified explanation of the abstract
This abstract first appeared for US patent application 17988376 titled 'TRANSFORMING SPEECH SIGNALS TO ATTENUATE SPEECH OF COMPETING INDIVIDUALS AND OTHER NOISE
Simplified Explanation
The patent application describes a method for reducing noise in speech signals during communication sessions using a machine learning model.
- Speech signals are received from a user during a communication session.
- The received speech signals contain noise, including speech from other individuals.
- A machine learning model is used to transform the received speech signals, reducing the amount of noise.
- The machine learning model is trained with speech of the user that meets a noise threshold, collected during one or more communication sessions.
Potential Applications
This technology could be applied in various communication devices and platforms to improve the quality of audio during calls, video conferences, and other forms of communication where noise reduction is important.
Problems Solved
1. Eliminates background noise in speech signals, improving the overall clarity of communication. 2. Enhances user experience by reducing distractions caused by noise during communication sessions.
Benefits
1. Improved speech signal quality. 2. Enhanced user experience. 3. Better communication efficiency.
Potential Commercial Applications
"Enhancing Communication Quality with Noise Reduction Technology"
Possible Prior Art
There are existing noise reduction technologies in audio processing software and hardware, but the specific application of a machine learning model trained with user speech data to reduce noise in real-time communication signals may be a novel approach.
Unanswered Questions
How does the machine learning model differentiate between the user's speech and background noise?
The machine learning model likely uses pattern recognition and training data to distinguish between the user's speech and other noise sources.
What is the impact of reducing noise on the overall bandwidth usage during communication sessions?
Reducing noise in speech signals may lead to more efficient data transmission and potentially lower bandwidth requirements, but the exact impact would depend on the specifics of the implementation.
Original Abstract Submitted
In one example embodiment, speech signals are received from a user during a communication session. The received speech signals contain noise including speech of other individuals. The received speech signals are transformed by a machine learning model to produce transformed speech signals corresponding to the received speech signals with a reduced amount of the noise. The machine learning model is trained with speech of the user satisfying a noise threshold and collected during one or more communication sessions.
