Bumble sales climbed in the latest quarter, driven by higher spending by users on its dating apps as prepandemic conditions have largely returned. But the online dating company trimmed its 2022 revenue range to $920 million to $930 million, down from its prior forecast of $934 million to $944 million, largely due to a higher impact from foreign currency movements. Its outlook for sales in the current quarter also fell short of Wall Street expectations.

Algorithmic Transparency in Action: How and Why Do Companies Disclose Information on Algorithms? Does the Accent of an Intelligent Conversational Agent Matter? What makes users reliant on the virtual assistant?

Amazon has reduced the price of the Echo Show 5 by $45. With the 53 percent discount, you can buy the smart display for $40, or just $5 more than it was during Prime Day. Amazon offers the device in a trio of colors – Charcoal, Deep Sea Blue and Glacier White. All three models are currently on sale. Like its bigger sibling, the Echo Show 5 includes a sunrise alarm feature, allowing the display to slowly brighten as a way to wake you gently during dark winter mornings.

Google has introduced a web version of its popular Read Along educational app for teaching children to read. The website includes Read Along the virtual assistant Diya, a voice-enabled AI guiding and correcting kids as they practice reading. The Read Along website operates much like the Android app. Children can pick from different stories and word games. Diya monitors the child, using Google's speech recognition technology to spot mistakes and places where they are having trouble.

Artificial intelligence (AI) is the ability of machines to mimic human capabilities in a way that we would consider'smart'. You most likely have come across – or are aware of – AI applications such as self-driving cars, facial recognition, chess or go players, security systems, or speech/voice recognition (for example, those used in an intelligent virtual assistant). In conventional computing, a programmer writes a computer program that precisely instructs a computer what to do to solve a particular problem. With AI, however, the programmer instead writes a program that allows the computer to learn to solve a problem by itself. That sounds like overdoing it, but this is really the way we do things.

Recent years brought an increasing interest in the application of machine learning algorithms in e-commerce, omnichannel marketing, and the sales industry. It is not only to the algorithmic advances but also to data availability, representing transactions, users, and background product information. Finding products related in different ways, i.e., substitutes and complements is essential for users' recommendations at the vendor's site and for the vendor - to perform efficient assortment optimization. The paper introduces a novel method for finding products' substitutes and complements based on the graph embedding Cleora algorithm. We also provide its experimental evaluation with regards to the state-of-the-art Shopper algorithm, studying the relevance of recommendations with surveys from industry experts. It is concluded that the new approach presented here offers suitable choices of recommended products, requiring a minimal amount of additional information. The algorithm can be used in various enterprises, effectively identifying substitute and complementary product options.

Recommender System (RS) is an important online application that affects billions of users every day. The mainstream RS ranking framework is composed of two parts: a Multi-Task Learning model (MTL) that predicts various user feedback, i.e., clicks, likes, sharings, and a Multi-Task Fusion model (MTF) that combines the multi-task outputs into one final ranking score with respect to user satisfaction. There has not been much research on the fusion model while it has great impact on the final recommendation as the last crucial process of the ranking. To optimize long-term user satisfaction rather than obtain instant returns greedily, we formulate MTF task as Markov Decision Process (MDP) within a recommendation session and propose a Batch Reinforcement Learning (RL) based Multi-Task Fusion framework (BatchRL-MTF) that includes a Batch RL framework and an online exploration. The former exploits Batch RL to learn an optimal recommendation policy from the fixed batch data offline for long-term user satisfaction, while the latter explores potential high-value actions online to break through the local optimal dilemma. With a comprehensive investigation on user behaviors, we model the user satisfaction reward with subtle heuristics from two aspects of user stickiness and user activeness. Finally, we conduct extensive experiments on a billion-sample level real-world dataset to show the effectiveness of our model. We propose a conservative offline policy estimator (Conservative-OPEstimator) to test our model offline. Furthermore, we take online experiments in a real recommendation environment to compare performance of different models. As one of few Batch RL researches applied in MTF task successfully, our model has also been deployed on a large-scale industrial short video platform, serving hundreds of millions of users.

Google has sued Sonos, alleging that its new voice assistant violates seven patents related to its own Google Assistant technology, CNET has reported. It's the latest salvo in a long-running smart speaker battle between the companies, with each suing and countersuing the other following a period when they worked together. "[Sonos has] started an aggressive and misleading campaign against our products, at the expense of our shared customers," a Google spokesperson said in a statement. Sonos' Voice Control assistant arrived in June, letting users give commands with the phrase "Hey Sonos," much like Amazon's Alexa or Google Assistant. In the complaint, Google said it "worked for years with Sonos engineers on the implementation of voice recognition and voice-activated devices control in Sonos products... even providing its Google Assistant software to Sonos for many years."

Speech AI can assist human agents in contact centers, power virtual assistants and digital avatars, generate live captioning in video conferencing, and much more. Under the hood, these voice-based technologies orchestrate a network of automatic speech recognition (ASR) and text-to-speech (TTS) pipelines to deliver intelligent, real-time responses. Building these real-time speech AI applications from scratch is no easy task. From setting up GPU-optimized development environments to deploying speech AI inferences using customized large transformer-based language models in under 300ms, speech AI pipelines require dedicated time, expertise, and investment. In this post, we walk through how you can simplify the speech AI development process by using NVIDIA Riva to run GPU-optimized applications.

Recommender systems are proving to be an invaluable tool for extracting user-relevant content helping users in their daily activities (e.g., finding relevant places to visit, content to consume, items to purchase). However, to be effective, these systems need to collect and analyze large volumes of personal data (e.g., location check-ins, movie ratings, click rates .. etc.), which exposes users to numerous privacy threats. In this context, recommender systems based on Federated Learning (FL) appear to be a promising solution for enforcing privacy as they compute accurate recommendations while keeping personal data on the users' devices. However, FL, and therefore FL-based recommender systems, rely on a central server that can experience scalability issues besides being vulnerable to attacks. To remedy this, we propose PEPPER, a decentralized recommender system based on gossip learning principles. In PEPPER, users gossip model updates and aggregate them asynchronously. At the heart of PEPPER reside two key components: a personalized peer-sampling protocol that keeps in the neighborhood of each node, a proportion of nodes that have similar interests to the former and a simple yet effective model aggregation function that builds a model that is better suited to each user. Through experiments on three real datasets implementing two use cases: a location check-in recommendation and a movie recommendation, we demonstrate that our solution converges up to 42% faster than with other decentralized solutions providing up to 9% improvement on average performance metric such as hit ratio and up to 21% improvement on long tail performance compared to decentralized competitors.