Well Siri, you’ve gone and done it again. This time Apple has to defend you against a Taiwan University. In a lawsuit filed with the US District Court for the Eastern District of Texas, The National Cheng King University (NCKU) states that Siri violates two voice-recognition patents and seeks a permanent sales ban of the iphone.
The two patents NCKU claims Apple’s Siri violates are US Patent No. 7,707,032, a “Method and System for Matching Speech Data” and US Patent No. 7,266,496, a “Speech recognition System”. As a result of Apple’s unlawful implementation of its most popular virtual assistant, The NCKU claims it suffered monetary damages and will continue to do so in the future. It is seeking a permanent sales ban of the iPhone 4S, plus monetary rewards and legal fees. However, we don’t know at the time of publishing this article, the precise value of these two patents.
Fact is, NCKU’s ‘032 patent was granted in 2010 after the University applied for it five years earlier. It is described as a rudimentary speech recognition algorithm determining similarities between fragments of speech.
A method and system used to determine the similarity between an input speech data and a sample speech data is provided. First, the input speech data is segmented into a plurality of input speech frames and the sample speech data is segmented into a plurality of sample speech frames. Then, the input speech frames and the sample speech frames are used to build a matching matrix, wherein the matching matrix comprises the distance values between each of the input speech frames and each of the sample speech frames. Next, the distance values are used to calculate a matching score. Finally, the similarity between the input speech data and the sample speech data is determined according to this matching score.
The second patent, ‘496 granted in 2003, is a more complex patent, and describes a complete speech recognition system based on ASIC (application specific integrated circuit) architecture. It even goes further, to include electrical components and software.
The present invention discloses a complete speech recognition system having a training button and a recognition button, and the whole system uses the application specific integrated circuit (ASIC) architecture for the design, and also uses the modular design to divide the speech processing into 4 modules: system control module, autocorrelation and linear predictive coefficient module, cepstrum module, and DTW recognition module. Each module forms an intellectual product (IP) component by itself. Each IP component can work with various products and application requirements for the design reuse to greatly shorten the time to market.
NCKU’s filing isn’t the first one Apple has had to face. In just one month, the Cupertino company had to deal with two lawsuits. The first one, filed by Zhi Zhen, a Chinese company, and the second one mentioned above. Apple’s iOS 6 coming this fall, will ship with an improved Siri and finally bring it to the iPad.Contact Us for News Tips, Corrections and Feedback