Apple is reportedly buying Shazam and its music identification tech

Engadget

In a bit of Friday afternoon news, TechCrunch reports that Apple plans to buy Shazam, the company behind the popular audio identification software and app. Apparently, the site's sources indicate the deal could be announced Monday, but it's quick to note the timing on these things isn't always solid. As you can imagine, rumored terms of the deal, including a sale price, aren't reliable just yet. The acquisition would give Apple ownership of the music, TV and movie identifying tech and a group of features it could easily take advantage of with its own products.


Radio Frequency Identification Tags, Memory Spots, and the Processing of Personally Identifiable Information, and Sensitive Data: When There Is No Balance Between Right and Wrong

AAAI Conferences

Novel medical applications and devices will shortly play a critical role in the diagnosis and storage of medical information in vivo on the patient’s body. Radio frequency identification (RFID) tags, and memory spots are probably going to be massively deployed on humans not just as a means to locate, and identify a subject but also to have access to sensitive information as medical records, genetic features, and pathological data. The role played by the advancement of technology in this sector is undoubtedly beneficial on the one hand because it solves many problems and deficiencies of the current situation, but on the other hand the collection of extremely sensitive data, like the genetic and pathological ones, must be treated with extreme caution, but probably even the most advanced safety features will not be sufficient to protect individuals from the illegal retrieval and processing of personally identifiable information and sensitive data. There will be a day in which striking a balance between what is useful, and what is too private to be known and disclosed will be extremely hard to accomplish for our decision-makers.


DeepWriterID: An End-to-end Online Text-independent Writer Identification System

arXiv.org Machine Learning

Owing to the rapid growth of touchscreen mobile terminals and pen-based interfaces, handwriting-based writer identification systems are attracting increasing attention for personal authentication, digital forensics, and other applications. However, most studies on writer identification have not been satisfying because of the insufficiency of data and difficulty of designing good features under various conditions of handwritings. Hence, we introduce an end-to-end system, namely DeepWriterID, employed a deep convolutional neural network (CNN) to address these problems. A key feature of DeepWriterID is a new method we are proposing, called DropSegment. It designs to achieve data augmentation and improve the generalized applicability of CNN. For sufficient feature representation, we further introduce path signature feature maps to improve performance. Experiments were conducted on the NLPR handwriting database. Even though we only use pen-position information in the pen-down state of the given handwriting samples, we achieved new state-of-the-art identification rates of 95.72% for Chinese text and 98.51% for English text.


NP Animacy Identification for Anaphora Resolution

AAAI Conferences

In anaphora resolution for English, animacy identification can play an integral role in the application of agreement restrictions between pronouns and candidates, and as a result, can improve the accuracy of anaphora resolution systems. In this paper, two methods for animacy identification are proposed and evaluated using intrinsic and extrinsic measures. The first method is a rule-based one which uses information about the unique beginners in WordNet to classify NPs on the basis of their animacy. The second method relies on a machine learning algorithm which exploits a WordNet enriched with animacy information for each sense. The effect of word sense disambiguation on the two methods is also assessed. The intrinsic evaluation reveals that the machine learning method reaches human levels of performance. The extrinsic evaluation demonstrates that animacy identification can be beneficial in anaphora resolution, especially in the cases where animate entities are identified with high precision.


NP Animacy Identification for Anaphora Resolution

Journal of Artificial Intelligence Research

In anaphora resolution for English, animacy identification can play an integral role in the application of agreement restrictions between pronouns and candidates, and as a result, can improve the accuracy of anaphora resolution systems. In this paper, two methods for animacy identification are proposed and evaluated using intrinsic and extrinsic measures. The first method is a rule-based one which uses information about the unique beginners in WordNet to classify NPs on the basis of their animacy. The second method relies on a machine learning algorithm which exploits a WordNet enriched with animacy information for each sense. The effect of word sense disambiguation on the two methods is also assessed. The intrinsic evaluation reveals that the machine learning method reaches human levels of performance. The extrinsic evaluation demonstrates that animacy identification can be beneficial in anaphora resolution, especially in the cases where animate entities are identified with high precision.