Multimodal models that jointly process audio and language hold great promise in audio understanding and are increasingly being adopted in the music domain. By allowing users to query via text and obtain information about a given audio input, these models have the potential to enable a variety of music understanding tasks via language-based interfaces. However, their evaluation poses considerable challenges, and it remains unclear how to effectively assess their ability to correctly interpret music-related inputs with current methods. Motivated by this, we introduce MuChoMusic, a benchmark for evaluating music understanding in multimodal language models focused on audio. MuChoMusic comprises 1,187 multiple-choice questions, all validated by human annotators, on 644 music tracks sourced from two publicly available music datasets, and covering a wide variety of genres. Questions in the benchmark are crafted to assess knowledge and reasoning abilities across several dimensions that cover fundamental musical concepts and their relation to cultural and functional contexts. Through the holistic analysis afforded by the benchmark, we evaluate five open-source models and identify several pitfalls, including an over-reliance on the language modality, pointing to a need for better multimodal integration. Data and code are open-sourced.
National Institute of Informatics（国立信息学研究所）；SOKENDAI（综合研究大学院大学）
This work present a music dataset named MusicTM-Dataset, which is utilized in improving the representation learning ability of different types of cross-modal retrieval (CMR). Little large music dataset including three modalities is available for learning representations for CMR. To collect a music dataset, we expand the original musical notation to synthesize audio and generated sheet-music image, and build musical notation based sheet-music image, audio clip and syllable-denotation text as fine-grained alignment, such that the MusicTM-Dataset can be exploited to receive shared representation …
The Swiss AI Lab, IDSIA, USI & SUPSI（瑞士人工智能实验室，IDSIA，卢加诺大学与瑞士南部应用科学与艺术大学）；Institute of Neuroinformatics, ETH Zurich（苏黎世联邦理工学院神经信息学研究所）；AI Initiative, KAUST（阿卜杜拉国王科技大学人工智能计划）
Digital audio processing tools offer music researchers the opportunity to examine both non-notated music and music as performance. This chapter summarises the types of information that can be extracted from audio as well as currently available audio tools for music corpus studies. The survey of extraction methods includes both a primer on signal processing and background theory on audio feature extraction. The survey of audio tools focuses on widely used tools, including both those with a graphical user interface, namely Audacity and Sonic Visualiser, and code-based tools written in the C/C++,…
As digital music production has become mainstream, the selection of appropriate virtual instruments plays a crucial role in determining the quality of music. To search the musical instrument samples or virtual instruments that make one's desired sound, music producers use their ears to listen and compare each instrument sample in their collection, which is time-consuming and inefficient. In this paper, we call this task as Musical Instrument Retrieval and propose a method for retrieving desired musical instruments using reference music mixture as a query. The proposed model consists of the Sin…
Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound
The Hong Kong University of Science（香港科学与技术大学）；Inner Mongolia University（内蒙古大学）；Beihang University（北京航空航天大学）；Queen Mary University of London（伦敦玛丽女王大学）；The Chinese University of Hong Kong（香港中文大学）；National University of Singapore（新加坡国立大学）；University of Surrey（萨里大学）；University of Rochester（罗切斯特大学）；Independent Researcher（独立研究者）
University of Vienna（维也纳大学）；University of Bamberg（班贝格大学）
We look into the connection between the musical and lyrical content of metal music by combining automated extraction of high-level audio features and quantitative text analysis on a corpus of 124.288 song lyrics from this genre. Based on this text corpus, a topic model was first constructed using Latent Dirichlet Allocation (LDA). For a subsample of 503 songs, scores for predicting perceived musical hardness/heaviness and darkness/gloominess were extracted using audio feature models. By combining both audio feature and text analysis, we (1) offer a comprehensive overview of the lyrical topics …
This paper introduces the jazznet Dataset, a dataset of fundamental jazz piano music patterns for developing machine learning (ML) algorithms in music information retrieval (MIR). The dataset contains 162520 labeled piano patterns, including chords, arpeggios, scales, and chord progressions with their inversions, resulting in more than 26k hours of audio and a total size of 95GB. The paper explains the dataset's composition, creation, and generation, and presents an open-source Pattern Generator using a method called Distance-Based Pattern Structures (DBPS), which allows researchers to easily …
Queen Mary University of London（伦敦玛丽女王大学）；NYU Shanghai（上海纽约大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）
Lyric interpretations can help people understand songs and their lyrics quickly, and can also make it easier to manage, retrieve and discover songs efficiently from the growing mass of music archives. In this paper we propose BART-fusion, a novel model for generating lyric interpretations from lyrics and music audio that combines a large-scale pre-trained language model with an audio encoder. We employ a cross-modal attention module to incorporate the audio representation into the lyrics representation to help the pre-trained language model understand the song from an audio perspective, while …
University of Rochester（罗切斯特大学）；Listent American Corp.（Listent American公司）
We introduce a dataset for facilitating audio-visual analysis of music performances. The dataset comprises 44 simple multi-instrument classical music pieces assembled from coordinated but separately recorded performances of individual tracks. For each piece, we provide the musical score in MIDI format, the audio recordings of the individual tracks, the audio and video recording of the assembled mixture, and ground-truth annotation files including frame-level and note-level transcriptions. We describe our methodology for the creation of the dataset, particularly highlighting our approaches for …
Note-Level Temporal Grounding of Musical Concepts in Large Audio-Language Models
Schulich School of Music, McGill University（麦吉尔大学舒利希音乐学院）；CIRMMT (Centre for Interdisciplinary Research in Music Media and Technology)（音乐媒体与技术跨学科研究中心（CIRMMT））；Courant Institute, New York University（纽约大学柯朗研究所）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学（MBZUAI））
Queen Mary University of London（伦敦玛丽女王大学）；Universal Music Group（环球音乐集团）
Content-based music information retrieval has seen rapid progress with the adoption of deep learning. Current approaches to high-level music description typically make use of classification models, such as in auto-tagging or genre and mood classification. In this work, we propose to address music description via audio captioning, defined as the task of generating a natural language description of music audio content in a human-like manner. To this end, we present the first music audio captioning model, MusCaps, consisting of an encoder-decoder with temporal attention. Our method combines convo…
Emotion is a complicated notion present in music that is hard to capture even with fine-tuned feature engineering. In this paper, we investigate the utility of state-of-the-art pre-trained deep audio embedding methods to be used in the Music Emotion Recognition (MER) task. Deep audio embedding methods allow us to efficiently capture the high dimensional features into a compact representation. We implement several multi-class classifiers with deep audio embeddings to predict emotion semantics in music. We investigate the effectiveness of L3-Net and VGGish deep audio embedding methods for music …
Queen Mary University of London（伦敦玛丽女王大学）；Universal Music Group（环球音乐集团）
As one of the most intuitive interfaces known to humans, natural language has the potential to mediate many tasks that involve human-computer interaction, especially in application-focused fields like Music Information Retrieval. In this work, we explore cross-modal learning in an attempt to bridge audio and language in the music domain. To this end, we propose MusCALL, a framework for Music Contrastive Audio-Language Learning. Our approach consists of a dual-encoder architecture that learns the alignment between pairs of music audio and descriptive sentences, producing multimodal embeddings t…
This paper aims to test whether a multi-modal approach for music emotion recognition (MER) performs better than a uni-modal one on high-level song features and lyrics. We use 11 song features retrieved from the Spotify API, combined lyrics features including sentiment, TF-IDF, and Anew to predict valence and arousal (Russell, 1980) scores on the Deezer Mood Detection Dataset (DMDD) (Delbouys et al., 2018) with 4 different regression models. We find that out of the 11 high-level song features, mainly 5 contribute to the performance, multi-modal features do better than audio alone when predictin…
Pronounced as "musician", the musicnn library contains a set of pre-trained musically motivated convolutional neural networks for music audio tagging: https://github.com/jordipons/musicnn. This repository also includes some pre-trained vgg-like baselines. These models can be used as out-of-the-box music audio taggers, as music feature extractors, or as pre-trained models for transfer learning. We also provide the code to train the aforementioned models: https://github.com/jordipons/musicnn-training. This framework also allows implementing novel models. For example, a musically motivated convol…
Music segmentation refers to the dual problem of identifying boundaries between, and labeling, distinct music segments, e.g., the chorus, verse, bridge etc. in popular music. The performance of a range of music segmentation algorithms has been shown to be dependent on the audio features chosen to represent the audio. Some approaches have proposed learning feature transformations from music segment annotation data, although, such data is time consuming or expensive to create and as such these approaches are likely limited by the size of their datasets. While annotated music segmentation data is…
Queen Mary University of London（伦敦玛丽女王大学）；Universal Music Group（环球音乐集团）
Audio representations for music information retrieval are typically learned via supervised learning in a task-specific fashion. Although effective at producing state-of-the-art results, this scheme lacks flexibility with respect to the range of applications a model can have and requires extensively annotated datasets. In this work, we pose the question of whether it may be possible to exploit weakly aligned text as the only supervisory signal to learn general-purpose music audio representations. To address this question, we design a multimodal architecture for music and language pre-training (…
Graduate School of Culture Technology, KAIST（韩国科学技术院文化技术研究生院）；NAVER Corp.（NAVER公司）
Audio-based music classification and tagging is typically based on categorical supervised learning with a fixed set of labels. This intrinsically cannot handle unseen labels such as newly added music genres or semantic words that users arbitrarily choose for music retrieval. Zero-shot learning can address this problem by leveraging an additional semantic space of labels where side information about the labels is used to unveil the relationship between each other. In this work, we investigate the zero-shot learning in the music domain and organize two different setups of side information. One i…
We present SingSong, a system that generates instrumental music to accompany input vocals, potentially offering musicians and non-musicians alike an intuitive new way to create music featuring their own voice. To accomplish this, we build on recent developments in musical source separation and audio generation. Specifically, we apply a state-of-the-art source separation algorithm to a large corpus of music audio to produce aligned pairs of vocals and instrumental sources. Then, we adapt AudioLM (Borsos et al., 2022) -- a state-of-the-art approach for unconditional audio generation -- to be sui…
University of Sheffield（谢菲尔德大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Queen Mary University of London（伦敦玛丽女王大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Michigan Ann Arbor（密歇根大学安娜堡分校）；Peking University（北京大学）；University of Tübingen（蒂宾根大学）；MPI-IS（马克斯·普朗克智能系统研究所）；Dartmouth College（达特茅斯学院）
The deep learning community has witnessed an exponentially growing interest in self-supervised learning (SSL). However, it still remains unexplored how to build a framework for learning useful representations of raw music waveforms in a self-supervised manner. In this work, we design Music2Vec, a framework exploring different SSL algorithmic components and tricks for music audio recordings. Our model achieves comparable results to the state-of-the-art (SOTA) music SSL model Jukebox, despite being significantly smaller with less than 2% of parameters of the latter. The model will be released on…
Preprint for a book chapter introducing Audio Content Analysis. With a focus on Music Information Retrieval systems, this chapter defines musical audio content, introduces the general process of audio content analysis, and surveys basic approaches to audio content analysis. The various tasks in Audio Content Analysis are categorized into three classes: music transcription, music performance analysis, and music identification and categorization. The examples for music transcription systems include music key detection, fundamental frequency detection, and music structure detection. Music perform…
Google Research（谷歌研究院）；Seoul National University（首尔大学）
Music tagging and content-based retrieval systems have traditionally been constructed using pre-defined ontologies covering a rigid set of music attributes or text queries. This paper presents MuLan: a first attempt at a new generation of acoustic models that link music audio directly to unconstrained natural language music descriptions. MuLan takes the form of a two-tower, joint audio-text embedding model trained using 44 million music recordings (370K hours) and weakly-associated, free-form text annotations. Through its compatibility with a wide range of music genres and text styles (includi…
Acoustics Research Institute, Austrian Academy of Sciences（奥地利科学院声学研究所）；Swiss Data Science Center, ETH Zürich（苏黎世联邦理工学院瑞士数据科学中心）
We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps in the range of tens of milliseconds. The proposed DNN structure was trained on audio signals containing music and musical instruments, separately, with 64-ms long gaps. The input to the DNN was the context, i.e., the signal surrounding the gap, transformed into time-frequency (TF) coefficients. Our results were compared to those obtained from a reference method based on linear predictive coding (LPC). For music, our …
We have built a music similarity search engine that lets video producers search by listenable music excerpts, as a complement to traditional full-text search. Our system suggests similar sounding track segments in a large music catalog by training a self-supervised convolutional neural network with triplet loss terms and musical transformations. Semi-structured user interviews demonstrate that we can successfully impress professional video producers with the quality of the search experience, and perceived similarities to query tracks averaged 7.8/10 in user testing. We believe this search tool…
Institute of Computational Perception, JKU Linz（林茨约翰·开普勒大学计算感知研究所）；Sony Computer Science Laboratories (CSL)（索尼计算机科学实验室）
Many music theoretical constructs (such as scale types, modes, cadences, and chord types) are defined in terms of pitch intervals---relative distances between pitches. Therefore, when computer models are employed in music tasks, it can be useful to operate on interval representations rather than on the raw musical surface. Moreover, interval representations are transposition-invariant, valuable for tasks like audio alignment, cover song detection and music structure analysis. We employ a gated autoencoder to learn fixed-length, invertible and transposition-invariant interval representations fr…
Dolby Laboratories（杜比实验室）；University of California San Diego（加利福尼亚大学圣地亚哥分校）
Music performance synthesis aims to synthesize a musical score into a natural performance. In this paper, we borrow recent advances in text-to-speech synthesis and present the Deep Performer -- a novel system for score-to-audio music performance synthesis. Unlike speech, music often contains polyphony and long notes. Hence, we propose two new techniques for handling polyphonic inputs and providing a fine-grained conditioning in a transformer encoder-decoder model. To train our proposed system, we present a new violin dataset consisting of paired recordings and scores along with estimated align…
Creation of images using generative adversarial networks has been widely adapted into multi-modal regime with the advent of multi-modal representation models pre-trained on large corpus. Various modalities sharing a common representation space could be utilized to guide the generative models to create images from text or even from audio source. Departing from the previous methods that solely rely on either text or audio, we exploit the expressiveness of both modality. Based on the fusion of text and audio, we create video whose content is consistent with the distinct modalities that are provid…
National Institute of Informatics（国立信息学研究所）；SOKENDAI（综合研究大学院大学）
Sheet music, audio, and lyrics are three main modalities during writing a song. In this paper, we propose an unsupervised generative adversarial alignment representation (UGAAR) model to learn deep discriminative representations shared across three major musical modalities: sheet music, lyrics, and audio, where a deep neural network based architecture on three branches is jointly trained. In particular, the proposed model can transfer the strong relationship between audio and sheet music to audio-lyrics and sheet-lyrics pairs by learning the correlation in the latent shared subspace. We apply …
Automatic Chord Estimation (ACE) is a fundamental task in Music Information Retrieval (MIR) and has applications in both music performance and MIR research. The task consists of segmenting a music recording or score and assigning a chord label to each segment. Although it has been a task in the annual benchmarking evaluation MIREX for over 10 years, ACE is not yet a solved problem, since performance has stagnated and modern systems have started to tune themselves to subjective training data. We propose DECIBEL, a new ACE system that exploits widely available MIDI and tab representations to imp…
Existing automatic music generation approaches that feature deep learning can be broadly classified into two types: raw audio models and symbolic models. Symbolic models, which train and generate at the note level, are currently the more prevalent approach; these models can capture long-range dependencies of melodic structure, but fail to grasp the nuances and richness of raw audio generations. Raw audio models, such as DeepMind's WaveNet, train directly on sampled audio waveforms, allowing them to produce realistic-sounding, albeit unstructured music. In this paper, we propose an automatic mu…
Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）
Music creation is typically composed of two parts: composing the musical score, and then performing the score with instruments to make sounds. While recent work has made much progress in automatic music generation in the symbolic domain, few attempts have been made to build an AI model that can render realistic music audio from musical scores. Directly synthesizing audio with sound sample libraries often leads to mechanical and deadpan results, since musical scores do not contain performance-level information, such as subtle changes in timing and dynamics. Moreover, while the task may sound li…
Stanford University（斯坦福大学）；Politecnico di Milano（米兰理工大学）；Politecnico di Torino（都灵理工大学）
Networked Music Performance (NMP) is envisioned as a potential game changer among Internet applications: it aims at revolutionizing the traditional concept of musical interaction by enabling remote musicians to interact and perform together through a telecommunication network. Ensuring realistic conditions for music performance, however, constitutes a significant engineering challenge due to extremely strict requirements in terms of audio quality and, most importantly, network delay. To minimize the end-to-end delay experienced by the musicians, typical implementations of NMP applications use …
Realistic music generation is a challenging task. When building generative models of music that are learnt from data, typically high-level representations such as scores or MIDI are used that abstract away the idiosyncrasies of a particular performance. But these nuances are very important for our perception of musicality and realism, so in this work we embark on modelling music in the raw audio domain. It has been shown that autoregressive models excel at generating raw audio waveforms of speech, but when applied to music, we find them biased towards capturing local signal structure at the ex…
