A method for operating a voice trigger is provided. In some implementations, the method is performed at an electronic device including one or more processors and memory storing instructions for execution by the one or more processors. The method includes receiving a sound input. The sound input may correspond to a spoken word or phrase, or a portion thereof. The method includes determining whether at least a portion of the sound input corresponds to a predetermined type of sound, such as a human voice. The method includes, upon a determination that at least a portion of the sound input corresponds to the predetermined type, determining whether the sound input includes predetermined content, such as a predetermined trigger word or phrase. The method also includes, upon a determination that the sound input includes the predetermined content, initiating a speech-based service, such as a voice-based digital assistant.

Voice trigger for a digital assistant

At an electronic device with a display, a microphone, and an input device: while the display is on, receiving user input via the input device, the user input meeting a predetermined condition; in accordance with receiving the user input meeting the predetermined condition, sampling audio input received via the microphone; determining whether the audio input comprises a spoken trigger; and in accordance with a determination that audio input comprises the spoken trigger, triggering a virtual assistant session.

Virtual assistant activation

Systems and processes for operating a digital assistant are provided. In one example, a method includes receiving a first speech input from a user. The method further includes identifying context information and determining a user intent based on the first speech input and the context information. The method further includes determining whether the user intent is to perform a task using a searching process or an object managing process. The searching process is configured to search data, and the object managing process is configured to manage objects. The method further includes, in accordance with a determination the user intent is to perform the task using the searching process, performing the task using the searching process; and in accordance with the determination that the user intent is to perform the task using the object managing process, performing the task using the object managing process.

Intelligent digital assistant in a multi-tasking environment

Music has serious effects on children's development. Music lyrics have become more violent and sexual over the years. However, the system for filtering explicit contents in music often does not work properly, not to mention that it takes a lot of time and effort to do it properly. In this study, we propose several machine learning models that automatically detect explicit contents in Korean lyrics and compare their performances. The proposed Bagging with selective vocabulary model outperformed not only the other competing models we designed, but also the filtering method that used the man-made profanity dictionary, which is a widely-used method to detect explicit contents in the industry. The proposed automated lyrics screening approach makes practical contributions to music industry, helping it significantly save time and effort for censoring harmful contents for the youths. The proposed approach is generalizable to other language settings as long as the same kinds of data used in the study are available.

Explicit Content Detection in Music Lyrics Using Machine Learning

In this paper, we describe a workflow for the data-driven acquisition and semantic scaling of a lexicon that covers lexical items from the lower end of the German language register—terms typically considered as rough, vulgar or obscene. Since the fine semantic representation of grades of obscenity can only inadequately be captured at the categorical level (e.g., obscene vs. non-obscene, or rough vs. vulgar), our main contribution lies in applying best-worst scaling, a rating methodology that has already been shown to be useful for emotional language, to capture the relative strength of obscenity of lexical items. We describe the empirical foundations for bootstrapping such a low-end lexicon for German by starting from manually supplied lexicographic categorizations of a small seed set of rough and vulgar lexical items and automatically enlarging this set by means of distributional semantics. We then determine the degrees of obscenity for the full set of all acquired lexical items by letting crowdworkers comparatively assess their pejorative grade using best-worst scaling. This semi-automatically enriched lexicon already comprises 3,300 lexical items and incorporates 33,000 vulgarity ratings. Using it as a seed lexicon for fully automatic lexical acquisition, we were able to raise its coverage up to slightly more than 11,000 entries.

/pdf/at-the-lower-end-of-language-exploring-the-vulgar-and-2fen6nh9qg.pdf

At the Lower End of Language—Exploring the Vulgar and Obscene Side of German

Information obtained nowadays often contains malicious contents. These malicious contents such as profane words have to be censored as they can influence the minds of the young ones and create hate among people. In censoring the profane words, this paper introduces a hybrid text censoring method which is based on Bayesian Filtering and Approximate String Matching techniques. The Bayesian filtering technique is used to detect the malicious contents (profane words) while the Approximate String Matching technique is used to enhance the effectiveness of detecting profane words. In evaluating the performance of the proposed system, the evaluation metrics of Precision, Recall, F-measure and MAE were used. The results show that Bayesian filtering technique can be used to filter profane words.

Muhammad Shurazi Sukhur

Papers

Text Censoring System for Filtering Malicious Content Using Approximate String Matching and Bayesian Filtering