Multi-pitch estimation is a decades-long research problem involving the detection of pitch activity associated with concurrent musical events within multi-instrument mixtures. Supervised learning techniques have demonstrated solid performance on more narrow characterizations of the task, but suffer from limitations concerning the shortage of large-scale and diverse polyphonic music datasets with multi-pitch annotations. We present a suite of self-supervised learning objectives for multi-pitch estimation, which encourage the concentration of support around harmonics, invariance to timbral transformations, and equivariance to geometric transformations. These objectives are sufficient to train an entirely convolutional autoencoder to produce multi-pitch salience-grams directly, without any fine-tuning. Despite training exclusively on a collection of synthetic single-note audio samples, our fully self-supervised framework generalizes to polyphonic music mixtures, and achieves performance comparable to supervised models trained on conventional multi-pitch datasets.

In recent years, machine learning, and in particular generative adversarial neural networks (GANs) and attention-based neural networks (transformers), have been successfully used to compose and generate music, both melodies and polyphonic pieces. Current research focuses foremost on style replication (eg. generating a Bach-style chorale) or style transfer (eg. classical to jazz) based on large amounts of recorded or transcribed music, which in turn also allows for fairly straight-forward "performance" evaluation. However, most of these models are not suitable for human-machine co-creation through live interaction, neither is clear, how such models and resulting creations would be evaluated. This article presents a thorough review of music representation, feature analysis, heuristic algorithms, statistical and parametric modelling, and human and automatic evaluation measures, along with a discussion of which approaches and models seem most suitable for live interaction.

Social media platforms are popular tools for disseminating targeted information during major public events like elections or pandemics. Systematic analysis of the message traffic can provide valuable insights into prevailing opinions and social dynamics among different segments of the population. We are specifically interested in influence spread, and in particular whether more deliberate influence operations can be detected. However, filtering out the essential messages with telltale influence indicators from the extensive and often chaotic social media traffic is a major challenge. In this paper we present a novel approach to extract influence indicators from messages circulating among groups of users discussing particular topics. We build upon the concept of a convo to identify influential authors who are actively promoting some particular agenda around that topic within the group. We focus on two influence indicators: the (control of) agenda and the use of emotional language.

This study explores the realm of knowledge-base question answering (KBQA). KBQA is considered a challenging task, particularly in parsing intricate questions into executable logical forms. Traditional semantic parsing (SP)-based methods require extensive data annotations, which result in significant costs. Recently, the advent of few-shot in-context learning, powered by large language models (LLMs), has showcased promising capabilities. Yet, fully leveraging LLMs to parse questions into logical forms in low-resource scenarios poses a substantial challenge. To tackle these hurdles, we introduce Interactive-KBQA, a framework designed to generate logical forms through direct interaction with knowledge bases (KBs). Within this framework, we have developed three generic APIs for KB interaction. For each category of complex question, we devised exemplars to guide LLMs through the reasoning processes. Our method achieves competitive results on the WebQuestionsSP, ComplexWebQuestions, KQA Pro, and MetaQA datasets with a minimal number of examples (shots). Importantly, our approach supports manual intervention, allowing for the iterative refinement of LLM outputs. By annotating a dataset with step-wise reasoning processes, we showcase our model's adaptability and highlight its potential for contributing significant enhancements to the field.

A new approach was put forward by Maman and Automatic music transcription (AMT) has achieved high accuracy Bermano [9] in which activations from an existing transcription for piano due to the availability of large, high-quality model are used instead of spectral features. In their work datasets such as MAESTRO and MAPS, but comparable this model is bootstrapped using synthetic audio-score pairs datasets are not yet available for other instruments. In recent and then retrained on the aligned scores. This process goes work, however, it has been demonstrated that aligning scores through several iterations of Expectation Maximisation [10] to transcription model activations can produce high quality to improve the results before a final transcription model is AMT training data for instruments other than piano.

Second gentleman Doug Emhoff recently said he and his wife Vice President Kamala Harris are "living" out the HBO series "Veep" during their time at the White House. Emhoff made the claim while appearing on Bravo's "Watch What Happens Live," telling host Andy Cohen that his and Harris' lives resemble the comedy centered on the antics of fictional Vice President Selina Meyer from the popular HBO comedy. During the segment, Cohen asked Emhoff, "Do you watch'Veep?' Have you ever seen'Veep?'" to which he responded, "We're living it." Second Gentleman Doug Emhoff recently claimed he and his wife, Vice President Harris, are "living" the HBO series "Veep." In the show, many of the comedic moments come from Meyer's gaffes, awkward social interactions and frustrations with the limits of her job and incompetence of her staff.

Seti is building a parallel, AI-powered software system for the observatory's core facility, the Very Large Array. Built between 1973 and 1981, the VLA comprises 28 large, 25m diameter, dish antennas spaced out across a desert plain. Imagine the satellite dishes you find on people's homes, just on a giant scale.

Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have a definitive answer. To avoid providing hallucinated answers to these unknown questions, existing studies typically investigate approaches to refusing to answer these questions. In this work, we propose a novel and scalable self-alignment method to utilize the LLM itself to enhance its response-ability to different types of unknown questions, being capable of not only refusing to answer but also providing explanation to the unanswerability of unknown questions. Specifically, the Self-Align method first employ a two-stage class-aware self-augmentation approach to generate a large amount of unknown question-response data. Then we conduct disparity-driven self-curation to select qualified data for fine-tuning the LLM itself for aligning the responses to unknown questions as desired. Experimental results on two datasets across four types of unknown questions validate the superiority of the Self-Align method over existing baselines in terms of three types of task formulation.

Sentiment analysis is a continuously explored area of text processing that deals with the computational analysis of opinions, sentiments, and subjectivity of text. However, this idea is not limited to text and speech, in fact, it could be applied to other modalities. In reality, humans do not express themselves in text as deeply as they do in music. The ability of a computational model to interpret musical emotions is largely unexplored and could have implications and uses in therapy and musical queuing. In this paper, two individual tasks are addressed. This study seeks to (1) predict the emotion of a musical clip over time and (2) determine the next emotion value after the music in a time series to ensure seamless transitions. Utilizing data from the Emotions in Music Database, which contains clips of songs selected from the Free Music Archive annotated with levels of valence and arousal as reported on Russel's circumplex model of affect by multiple volunteers, models are trained for both tasks. Overall, the performance of these models reflected that they were able to perform the tasks they were designed for effectively and accurately.

Theory of Mind (ToM) is the cognitive capability to perceive and ascribe mental states to oneself and others. Recent research has sparked a debate over whether large language models (LLMs) exhibit a form of ToM. However, existing ToM evaluations are hindered by challenges such as constrained scope, subjective judgment, and unintended contamination, yielding inadequate assessments. To address this gap, we introduce ToMBench with three key characteristics: a systematic evaluation framework encompassing 8 tasks and 31 abilities in social cognition, a multiple-choice question format to support automated and unbiased evaluation, and a build-from-scratch bilingual inventory to strictly avoid data leakage. Based on ToMBench, we conduct extensive experiments to evaluate the ToM performance of 10 popular LLMs across tasks and abilities. We find that even the most advanced LLMs like GPT-4 lag behind human performance by over 10% points, indicating that LLMs have not achieved a human-level theory of mind yet. Our aim with ToMBench is to enable an efficient and effective evaluation of LLMs' ToM capabilities, thereby facilitating the development of LLMs with inherent social intelligence.