We propose a novel system that takes as an input body movements of a musician playing a musical instrument and generates music in an unsupervised setting. Learning to generate multi-instrumental music from videos without labeling the instruments is a challenging problem. To achieve the transformation, we built a pipeline named 'Multi-instrumentalistNet' (MI Net). At its base, the pipeline learns a discrete latent representation of various instruments music from log-spectrogram using a Vector Quantized Variational Autoencoder (VQ-VAE) with multi-band residual blocks. The pipeline is then trained along with an autoregressive prior conditioned on the musician's body keypoints movements encoded by a recurrent neural network. Joint training of the prior with the body movements encoder succeeds in the disentanglement of the music into latent features indicating the musical components and the instrumental features. The latent space results in distributions that are clustered into distinct instruments from which new music can be generated. Furthermore, the VQ-VAE architecture supports detailed music generation with additional conditioning. We show that a Midi can further condition the latent space such that the pipeline will generate the exact content of the music being played by the instrument in the video. We evaluate MI Net on two datasets containing videos of 13 instruments and obtain generated music of reasonable audio quality, easily associated with the corresponding instrument, and consistent with the music audio content.
Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）
This paper presents a neural network model to generate virtual violinist's 3-D skeleton movements from music audio. Improved from the conventional recurrent neural network models for generating 2-D skeleton data in previous works, the proposed model incorporates an encoder-decoder architecture, as well as the self-attention mechanism to model the complicated dynamics in body movement sequences. To facilitate the optimization of self-attention model, beat tracking is applied to determine effective sizes and boundaries of the training examples. The decoder is accompanied with a refining network …
MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Massachusetts Institute of Technology（麻省理工学院）
In this paper, we introduce Foley Music, a system that can synthesize plausible music for a silent video clip about people playing musical instruments. We first identify two key intermediate representations for a successful video to music generator: body keypoints from videos and MIDI events from audio recordings. We then formulate music generation from videos as a motion-to-MIDI translation problem. We present a Graph$-$Transformer framework that can accurately predict MIDI event sequences in accordance with the body movements. The MIDI event can then be converted to realistic music using an …
This paper presents a generative AI model for automated music composition with LSTM networks that takes a novel approach at encoding musical information which is based on movement in music rather than absolute pitch. Melodies are encoded as a series of intervals rather than a series of pitches, and chords are encoded as the set of intervals that each chord note makes with the melody at each timestep. Experimental results show promise as they sound musical and tonal. There are also weaknesses to this method, mainly excessive modulations in the compositions, but that is expected from the nature …
Dance-to-Music Generation with Encoder-based Textual Inversion
Institute of Automation, CAS（中国科学院自动化研究所）；School of Artificial Intelligence, UCAS（中国科学院大学人工智能学院）；University of Chinese Academy of Sciences（中国科学院大学）；Kuaishou Technology（快手科技）；University of Konstanz（康斯坦茨大学）；National Cheng-Kung University（成功大学）
Many social media users prefer consuming content in the form of videos rather than text. However, in order for content creators to produce videos with a high click-through rate, much editing is needed to match the footage to the music. This posts additional challenges for more amateur video makers. Therefore, we propose a novel attention-based model VMT (Video-Music Transformer) that automatically generates piano scores from video frames. Using music generated from models also prevent potential copyright infringements that often come with using existing music. To the best of our knowledge, the…
Shanghai Jiao Tong University（上海交通大学）；Music Tech Lab, DynamiX（音乐科技实验室，DynamiX）；Shanghai AI Laboratory（上海人工智能实验室）；Beijing Film Academy（北京电影学院）；Tsinghua University（清华大学）；McGill University（麦吉尔大学）；The Chinese University of Hong Kong（香港中文大学）
LTCI（电信通信实验室）；Télécom Paris（巴黎电信学院）；Institut Polytechnique de Paris（巴黎理工学院）
Extracting pitch information from music recordings is a challenging but important problem in music signal processing. Frame-wise transcription or multi-pitch estimation aims for detecting the simultaneous activity of pitches in polyphonic music recordings and has recently seen major improvements thanks to deep-learning techniques, with a variety of proposed network architectures. In this paper, we realize different architectures based on CNNs, the U-net structure, and self-attention components. We propose several modifications to these architectures including self-attention modules for skip co…
University of Oslo（奥斯陆大学）；Australian National University（澳大利亚国立大学）
Sound and movement are closely coupled, particularly in dance. Certain audio features have been found to affect the way we move to music. Is this relationship between sound and movement something which can be modelled using machine learning? This work presents initial experiments wherein high-level audio features calculated from a set of music pieces are included in a movement generation model trained on motion capture recordings of improvised dance. Our results indicate that the model learns to generate realistic dance movements which vary depending on the audio features.
Composing for a film requires developing an understanding of the film, its characters and the film aesthetic choices made by the director. We propose using existing visual analysis systems as a core technology for film music generation. We extract film features including main characters and their emotions to develop a computer understanding of the film's narrative arc. This arc is combined with visually analyzed director aesthetic choices including pacing and levels of movement. Two systems are presented, the first using a robotic film composer and marimbist to generate film scores in real-tim…
MIT（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Recent deep learning approaches have achieved impressive performance on visual sound separation tasks. However, these approaches are mostly built on appearance and optical flow like motion feature representations, which exhibit limited abilities to find the correlations between audio signals and visual points, especially when separating multiple instruments of the same types, such as multiple violins in a scene. To address this, we propose "Music Gesture," a keypoint-based structured representation to explicitly model the body and finger movements of musicians when they perform music. We first…
QEAN: Quaternion-Enhanced Attention Network for Visual Dance Generation
Guangdong University of Technology（广东工业大学）；Huizhou University（惠州学院）；Guangdong Mechanical and Electrical College（广东机电职业技术学院）；University of Western Australia（西澳大学）
From Textural Counterpoint to Feature Encoding: A Multi-Dimensional Machine Representation Study of Haydn's "The Lark" Integrating Electroacoustic Analysis
Shenyang Conservatory of Music（沈阳音乐学院）；Education Information Center, Shenyang Conservatory of Music（沈阳音乐学院教育信息中心）
Synthesizing human motion through learning techniques is becoming an increasingly popular approach to alleviating the requirement of new data capture to produce animations. Learning to move naturally from music, i.e., to dance, is one of the more complex motions humans often perform effortlessly. Each dance movement is unique, yet such movements maintain the core characteristics of the dance style. Most approaches addressing this problem with classical convolutional and recursive neural models undergo training and variability issues due to the non-Euclidean geometry of the motion manifold stru…
Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation
College of Computer Science and Technology, Harbin Engineering University（哈尔滨工程大学计算机科学与技术学院）；Shanghai Academy of Artificial Intelligence for Science（上海人工智能科学研究院）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；State Key Laboratory of Space-Ground Integrated Information Technology（空间地面一体化信息技术创新实验室）
Exploring Multi-Modal Control in Music-Driven Dance Generation
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Peng Cheng Laboratory（鹏城实验室）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）
It is still an interesting and challenging problem to synthesize a vivid and realistic singing face driven by music signal. In this paper, we present a method for this task with natural motions of the lip, facial expression, head pose, and eye states. Due to the coupling of the mixed information of human voice and background music in common signals of music audio, we design a decouple-and-fuse strategy to tackle the challenge. We first decompose the input music audio into human voice stream and background music stream. Due to the implicit and complicated correlation between the two-stream inpu…
We present a novel system that gets as an input video frames of a musician playing the piano and generates the music for that video. Generation of music from visual cues is a challenging problem and it is not clear whether it is an attainable goal at all. Our main aim in this work is to explore the plausibility of such a transformation and to identify cues and components able to carry the association of sounds with visual events. To achieve the transformation we built a full pipeline named `\textit{Audeo}' containing three components. We first translate the video frames of the keyboard and the…
KTH Royal Institute of Technology（皇家理工学院）；Nanyang Technological University（南洋理工大学）；National Institute of Informatics（情报学研究所）；University of Copenhagen（哥本哈根大学）
Inria（法国国家信息与自动化研究所）；Ensta ParisTech（巴黎高等先进技术学院）；University of Bordeaux（波尔多大学）；KTH Royal Institute of Technology（KTH皇家理工学院）
Dance requires skillful composition of complex movements that follow rhythmic, tonal and timbral features of music. Formally, generating dance conditioned on a piece of music can be expressed as a problem of modelling a high-dimensional continuous motion signal, conditioned on an audio signal. In this work we make two contributions to tackle this problem. First, we present a novel probabilistic autoregressive architecture that models the distribution over future poses with a normalizing flow conditioned on previous poses as well as music context, using a multimodal transformer encoder. Second,…
Beat-It: Beat-Synchronized Multi-Condition 3D Dance Generation
South China University of Technology（华南理工大学）；Guangdong Engineering Center for Large Model and GenAI Technology（广东省大模型与生成式人工智能技术工程中心）；Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information（广东省计算智能与网络空间信息重点实验室）；The Hong Kong Polytechnic University（香港理工大学）；Singapore Management University（新加坡管理大学）
Waseda University（早稻田大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Honda Research Institute Japan（日本本田研究所）
Synthesizing human's movements such as dancing is a flourishing research field which has several applications in computer graphics. Recent studies have demonstrated the advantages of deep neural networks (DNNs) for achieving remarkable performance in motion and music tasks with little effort for feature pre-processing. However, applying DNNs for generating dance to a piece of music is nevertheless challenging, because of 1) DNNs need to generate large sequences while mapping the music input, 2) the DNN needs to constraint the motion beat to the music, and 3) DNNs require a considerable amount …
Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model
Ulsan National Institute of Science and Technology, South Korea（乌山国立科学技术研究院，韩国）；Daegu Gyeongbuk Institute of Science and Technology, South Korea（大邱庆北科学技术研究院，韩国）
