Related papers: Evaluating Interval-based Tokenization for Pitch R…
AI-based music generation has made significant progress in recent years. However, generating symbolic music that is both long-structured and expressive remains a significant challenge. In this paper, we propose PerceiverS (Segmentation and…
Timbre allows us to distinguish between sounds even when they share the same pitch and loudness, playing an important role in music, instrument recognition, and speech. Traditional approaches, such as frequency analysis or machine learning,…
Extraction of symbolic information from signals is an active field of research enabling numerous applications especially in the Musical Information Retrieval domain. This complex task, that is also related to other topics such as pitch…
Automatic Music Transcription (AMT), inferring musical notes from raw audio, is a challenging task at the core of music understanding. Unlike Automatic Speech Recognition (ASR), which typically focuses on the words of a single speaker, AMT…
Discrete audio representations, termed audio tokens, are broadly categorized into semantic and acoustic tokens, typically generated through unsupervised tokenization of continuous audio representations. However, their applicability to…
Tokenizers provide the fundamental basis through which text is represented and processed by language models (LMs). Despite the importance of tokenization, its role in LM performance and behavior is poorly understood due to the challenge of…
Recently, we proposed a self-attention based music tagging model. Different from most of the conventional deep architectures in music information retrieval, which use stacked 3x3 filters by treating music spectrograms as images, the…
Time series forecasting plays a vital role in supporting decision-making across a wide range of critical applications, including energy, healthcare, and finance. Despite recent advances, forecasting accuracy remains limited due to the…
Stimulus decoding of functional Magnetic Resonance Imaging (fMRI) data with machine learning models has provided new insights about neural representational spaces and task-related dynamics. However, the scarcity of labelled (task-related)…
Automatic music transcription (AMT) is one of the most challenging tasks in the music information retrieval domain. It is the process of converting an audio recording of music into a symbolic representation containing information about the…
Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. These tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation.…
Recent years have witnessed a growing interest in research related to the detection of piano pedals from audio signals in the music information retrieval community. However, to our best knowledge, recent generative models for symbolic music…
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…
Learning symbolic music representations, especially disentangled representations with probabilistic interpretations, has been shown to benefit both music understanding and generation. However, most models are only applicable to short-term…
We present an approach for recommending a music track for a given video, and vice versa, based on both their temporal alignment and their correspondence at an artistic level. We propose a self-supervised approach that learns this…
Sequence-to-sequence (seq2seq) models are prevalent in semantic parsing, but have been found to struggle at out-of-distribution compositional generalization. While specialized model architectures and pre-training of seq2seq models have been…
Cadences are complex structures that have been driving music from the beginning of contrapuntal polyphony until today. Detecting such structures is vital for numerous MIR tasks such as musicological analysis, key detection, or music…
Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises the encodings of…
This paper presents a novel evaluation approach to text-based speaker diarization (SD), tackling the limitations of traditional metrics that do not account for any contextual information in text. Two new metrics are proposed, Text-based…
Most modern approaches for audio processing are opaque, in the sense that they do not provide an explanation for their decisions. For this reason, various methods have been proposed to explain the outputs generated by these models. Good…