Related papers: MULTIMODAL ANALYSIS: Informed content estimation a…
We consider the question: what can be learnt by looking at and listening to a large number of unlabelled videos? There is a valuable, but so far untapped, source of information contained in the video itself -- the correspondence between the…
We introduce a new method for generating text, and in particular song lyrics, based on the speech-like acoustic qualities of a given audio file. We repurpose a vocal source separation algorithm and an acoustic model trained to recognize…
Speech enhancement and speech separation are two related tasks, whose purpose is to extract either one or more target speech signals, respectively, from a mixture of sounds generated by several sources. Traditionally, these tasks have been…
Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such…
A main challenge in applying deep learning to music processing is the availability of training data. One potential solution is Multi-task Learning, in which the model also learns to solve related auxiliary tasks on additional datasets to…
This paper targets the perceptual task of separating the different interacting voices, i.e., monophonic melodic streams, in a polyphonic musical piece. We target symbolic music, where notes are explicitly encoded, and model this task as a…
Sentiment analysis is a research topic focused on analysing data to extract information related to the sentiment that it causes. Applications of sentiment analysis are wide, ranging from recommendation systems, and marketing to customer…
The need for multimodal data integration arises naturally when multiple complementary sets of features are measured on the same sample. Under a dependent multifactor model, we develop a fully data-driven orchestrated approximate message…
Target speech separation refers to isolating target speech from a multi-speaker mixture signal by conditioning on auxiliary information about the target speaker. Different from the mainstream audio-visual approaches which usually require…
The mood of a song is a highly relevant feature for exploration and recommendation in large collections of music. These collections tend to require automatic methods for predicting such moods. In this work, we show that listening-based…
In this paper, we present our solutions for emotion recognition in the sub-challenges of Multimodal Emotion Recognition Challenge (MER2024). To mitigate the modal competition issue between audio and text, we adopt an early fusion strategy…
Mood recognition is an important problem in music informatics and has key applications in music discovery and recommendation. These applications have become even more relevant with the rise of music streaming. Our work investigates the…
In many machine learning systems that jointly learn from multiple modalities, a core research question is to understand the nature of multimodal interactions: how modalities combine to provide new task-relevant information that was not…
Lyrics transcription of polyphonic music is challenging because singing vocals are corrupted by the background music. To improve the robustness of lyrics transcription to the background music, we propose a strategy of combining the features…
The current paradigm for creating and deploying immersive audio content is based on audio objects, which are composed of an audio track and position metadata. While rendering an object-based production into a multichannel mix is…
How does textual representation of audio relate to the Large Language Model's (LLMs) learning about the audio world? This research investigates the extent to which LLMs can be prompted to generate audio, despite their primary training in…
Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding isolated source signals. Such datasets can be extremely…
In the real world, where information is abundant and diverse across different modalities, understanding and utilizing various data types to improve retrieval systems is a key focus of research. Multimodal composite retrieval integrates…
We propose a novel approach to multimodal sentiment analysis using deep neural networks combining visual analysis and natural language processing. Our goal is different than the standard sentiment analysis goal of predicting whether a…
A learning path is proposed starting from the characterization of a sound wave, showing how human beings emit articulate sounds in the language, introducing psychoacoustics, i.e. how the sound interacts with ears and it is transduced into…