High-quality data labeling from specific domains is costly and human time-consuming. In this work, we propose a self-supervised domain adaptation method, based upon an iterative pseudo-forced alignment algorithm. The produced alignments are employed to customize an end-to-end Automatic Speech Recognition (ASR) and iteratively refined. The algorithm is fed with frame-wise character posteriors produced by a seed ASR, trained with out-of-domain data, and optimized throughout a Connectionist Temporal Classification (CTC) loss. The alignments are computed iteratively upon a corpus of broadcast TV. The process is repeated by reducing the quantity of text to be aligned or expanding the alignment window until finding the best possible audio-text alignment. The starting timestamps, or temporal anchors, are produced uniquely based on the confidence score of the last aligned utterance. This score is computed with the paths of the CTC-alignment matrix. With this methodology, no human-revised text references are required. Alignments from long audio files with low-quality transcriptions, like TV captions, are filtered out by confidence score and ready for further ASR adaptation. The obtained results, on both the Spanish RTVE2022 and CommonVoice databases, underpin the feasibility of using CTC-based systems to perform: highly accurate audio-text alignments, domain adaptation and semi-supervised training of end-to-end ASR.

Internet based businesses and products (e.g. e-commerce, music streaming) are becoming more and more sophisticated every day with a lot of focus on improving customer satisfaction. A core way they achieve this is by providing customers with an easy access to their products by structuring them in catalogues using navigation bars and providing recommendations. We refer to these catalogues as product concepts, e.g. product categories on e-commerce websites, public playlists on music streaming platforms. These product concepts typically contain products that are linked with each other through some common features (e.g. a playlist of songs by the same artist). How they are defined in the backend of the system can be different for different products. In this work, we represent product concepts using database queries and tackle two learning problems. First, given sets of products that all belong to the same unknown product concept, we learn a database query that is a representation of this product concept. Second, we learn product concepts and their corresponding queries when the given sets of products are associated with multiple product concepts. To achieve these goals, we propose two approaches that combine the concepts of PU learning with Decision Trees and Clustering. Our experiments demonstrate, via a simulated setup for a music streaming service, that our approach is effective in solving these problems.

Autofarm is considering adding machine learning and artificial intelligence to its DEX aggregators, AutoSwap.

Frank Pavich is the director of "Jodorowsky's Dune," a documentary about the Chilean filmmaker Alejandro Jodorowsky's attempt to film a version of "Dune" in the mid-1970s. I was recently shown some frames from a film that I had never heard of: Alejandro Jodorowsky's 1976 version of "Tron." The actors, unfamiliar to me, looked fantastic in their roles. The costumes and lighting worked together perfectly. The images glowed with an extravagant and psychedelic sensibility that felt distinctly Jodorowskian.

According to Artificial Intelligence, this is the best Superman for James Gunn's new DC Universe. Supermanalso called Clark Kent y Kal-El.

Using artificial intelligence, Cornell University engineers have simplified … In this work, the group developed four machine learning models for …

In this week's World Reimagined, we will look at the rapidly evolving world of Artificial Intelligence (AI), some of its players, and what …

Artificial Intelligence is poised to create a seismic shift in entertainment, and the technology isn't just in development. It's arrived and Hollywood needs to be prepared. That was the message of a SAG-AFTRA-hosted CES panel, as AI-driven tools permeated the consumer tech show's exhibition halls. Nina Schick, author and advisor on generative AI, projected that 90 percent of content may be -- at least in part -- AI-generated by 2025. She further predicted that everyone in the audience would be planning to use some form of generative AI within the month.

The year 2022 was jam-packed with advances in artificial intelligence, from the release of image generators like DALL-E 2 and text generators like Cicero to a flurry of developments in the self-driving car industry. And then, on November 30, OpenAI released ChatGPT, arguably the smartest, funniest, most humanlike chatbot to date. In the weeks since, ChatGPT has become an internet sensation. If you've spent any time on social media recently, you've probably seen screenshots of it describing Karl Marx's theory of surplus value in the style of a Taylor Swift song or explaining how to remove a sandwich from a VCR in the style of the King James Bible. There are hundreds of examples like that.

Every cat owner knows that you don't have to observe the animals for long to know they are highly intelligent beings. Despite having relatively small brains, studies have shown felines have high emotional intelligence and a great willingness to adapt, making them some of the smartest creatures in the animal kingdom. But how to breeds stack up when it comes to intelligence? As a study this month revealed the most intelligent breeds of dogs, we delve into which breeds of cats can be crowned the cleverest. Does it respond to its own name? People tend to assume that cat's cannot learn their own names, unlike dogs. But research from Sophia University in Japan revealed that cats do recognise when their name is being called.