Cerence. has filed a patent for a method to prevent unauthorized use of speech signals by applying a watermark signal. The method involves generating an encoded watermark signal based on the original speech signal’s spectrogram and a selected phase sequence. GlobalData’s report on Cerence gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Cerence, Smart voice assistant was a key innovation area identified from patents. Cerence's grant share as of January 2024 was 76%. Grant share is based on the ratio of number of grants to total number of patents.
Watermarking method for speech signals to prevent unauthorized use
The patent application (Publication Number: US20240038249A1) describes a method for applying a watermark signal to a speech signal to prevent unauthorized use. The method involves receiving an original speech signal, determining a corresponding spectrogram, selecting a phase sequence, and generating an encoded watermark signal based on the spectrogram and phase sequence. Additional steps include taking the magnitude of the original speech spectrogram, applying bit encoding, and determining a frequency-dependent gain factor. The encoded watermark can be stored for authenticating future speech signals and may include words spoken in the original speech signal with associated sequence positions and start/end times.
Furthermore, the patent application includes a non-transitory computer-readable medium with instructions for applying the watermark signal to a speech signal. The processor executes operations such as receiving the original speech signal, determining the corresponding spectrogram, selecting a phase sequence, and generating the encoded watermark signal. Additional operations involve applying bit encoding and utilizing short-time Fourier transform (STFT) to determine the frequency and phase content of each frame of the original input signal. The patent also covers a method for applying a watermark signal to an audio signal containing speech content to prevent unauthorized use, where the encoded watermark signal defines the allowed usage of the original audio signal, which is then transmitted as an encoded audio signal.
To know more about GlobalData’s detailed insights on Cerence, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
