Co-creativity in music refers to two or more musicians or musical agents interacting with one another by composing or improvising music. However, this is a very subjective process and each musician has their own preference as to which improvisation is better for some context. In this paper, we aim to create a measure based on total information flow to quantitatively evaluate the co-creativity process in music. In other words, our measure is an indication of how "good" a creative musical process is. Our main hypothesis is that a good musical creation would maximize information flow between the participants captured by music voices recorded in separate tracks. We propose a method to compute the information flow using pre-trained generative models as entropy estimators. We demonstrate how our method matches with human perception using a qualitative study.
This paper introduces a new approach to sound source localization using head-related transfer function (HRTF) characteristics, which enable precise full-sphere localization from raw data. While previous research focused primarily on using extensive microphone arrays in the frontal plane, this arrangement often encountered limitations in accuracy and robustness when dealing with smaller microphone arrays. Our model proposes using both time and frequency domain for sound source localization while utilizing Deep Learning (DL) approach. The performance of our proposed model, surpasses the current state-of-the-art results. Specifically, it boasts an average angular error of $0.24 degrees and an average Euclidean distance of 0.01 meters, while the known state-of-the-art gives average angular error of 19.07 degrees and average Euclidean distance of 1.08 meters. This level of accuracy is of paramount importance for a wide range of applications, including robotics, virtual reality, and aiding individuals with cochlear implants (CI).
Deep learning models require large amounts of clean data to acheive good performance. To avoid the cost of expensive data acquisition, researchers use the abundant data available on the internet. This raises significant privacy concerns on the potential misuse of personal data for model training without authorisation. Recent works such as CUDA propose solutions to this problem by adding class-wise blurs to make datasets unlearnable, i.e a model can never use the acquired dataset for learning. However these methods often reduce the quality of the data making it useless for practical applications. We introduce PosCUDA, a position based convolution for creating unlearnable audio datasets. PosCUDA uses class-wise convolutions on small patches of audio. The location of the patches are based on a private key for each class, hence the model learns the relations between positional blurs and labels, while failing to generalize. We empirically show that PosCUDA can achieve unlearnability while maintaining the quality of the original audio datasets. Our proposed method is also robust to different audio feature representations such as MFCC, raw audio and different architectures such as transformers, convolutional networks etc.
The ''pretraining-and-finetuning'' paradigm has become a norm for training domain-specific models in natural language processing and computer vision. In this work, we aim to examine this paradigm for symbolic music generation through leveraging the largest ever symbolic music dataset sourced from the MuseScore forum. We first pretrain a large unconditional transformer model using 1.5 million songs. We then propose a simple technique to equip this pretrained unconditional music transformer model with instrument and genre controls by finetuning the model with additional control tokens. Our proposed representation offers improved high-level controllability and expressiveness against two existing representations. The experimental results show that the proposed model can successfully generate music with user-specified instruments and genre. In a subjective listening test, the proposed model outperforms the pretrained baseline model in terms of coherence, harmony, arrangement and overall quality.
We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on explicitly disentangling speech representations to separately encode speaker characteristics and linguistic content. However, disentangling speech representations to capture such attributes using task-specific loss terms can lead to information loss by discarding finer nuances of the original signal. In this work, instead of explicitly disentangling attributes with loss terms, we present a framework to train a controllable voice conversion model on entangled speech representations derived from self-supervised learning and speaker verification models. First, we develop techniques to derive prosodic information from the audio signal and SSL representations to train predictive submodules in the synthesis model. Next, we propose a training strategy to iteratively improve the synthesis model for voice conversion, by creating a challenging training objective using self-synthesized examples. In this training approach, the current state of the synthesis model is used to generate voice-converted variations of an utterance, which serve as inputs for the reconstruction task, ensuring a continuous and purposeful refinement of the model. We demonstrate that incorporating such self-synthesized examples during training improves the speaker similarity of generated speech as compared to a baseline voice conversion model trained solely on heuristically perturbed inputs. SelfVC is trained without any text and is applicable to a range of tasks such as zero-shot voice conversion, cross-lingual voice conversion, and controllable speech synthesis with pitch and pace modifications. SelfVC achieves state-of-the-art results in zero-shot voice conversion on metrics evaluating naturalness, speaker similarity, and intelligibility of synthesized audio.
In deep learning research, many melody extraction models rely on redesigning neural network architectures to improve performance. In this paper, we propose an input feature modification and a training objective modification based on two assumptions. First, harmonics in the spectrograms of audio data decay rapidly along the frequency axis. To enhance the model's sensitivity on the trailing harmonics, we modify the Combined Frequency and Periodicity (CFP) representation using discrete z-transform. Second, the vocal and non-vocal segments with extremely short duration are uncommon. To ensure a more stable melody contour, we design a differentiable loss function that prevents the model from predicting such segments. We apply these modifications to several models, including MSNet, FTANet, and a newly introduced model, PianoNet, modified from a piano transcription network. Our experimental results demonstrate that the proposed modifications are empirically effective for singing melody extraction.
Diffusion models have shown promising results in cross-modal generation tasks, including text-to-image and text-to-audio generation. However, generating music, as a special type of audio, presents unique challenges due to limited availability of music data and sensitive issues related to copyright and plagiarism. In this paper, to tackle these challenges, we first construct a state-of-the-art text-to-music model, MusicLDM, that adapts Stable Diffusion and AudioLDM architectures to the music domain. We achieve this by retraining the contrastive language-audio pretraining model (CLAP) and the Hifi-GAN vocoder, as components of MusicLDM, on a collection of music data samples. Then, to address the limitations of training data and to avoid plagiarism, we leverage a beat tracking model and propose two different mixup strategies for data augmentation: beat-synchronous audio mixup and beat-synchronous latent mixup, which recombine training audio directly or via a latent embeddings space, respectively. Such mixup strategies encourage the model to interpolate between musical training samples and generate new music within the convex hull of the training data, making the generated music more diverse while still staying faithful to the corresponding style. In addition to popular evaluation metrics, we design several new evaluation metrics based on CLAP score to demonstrate that our proposed MusicLDM and beat-synchronous mixup strategies improve both the quality and novelty of generated music, as well as the correspondence between input text and generated music.
Universal source separation (USS) is a fundamental research task for computational auditory scene analysis, which aims to separate mono recordings into individual source tracks. There are three potential challenges awaiting the solution to the audio source separation task. First, previous audio source separation systems mainly focus on separating one or a limited number of specific sources. There is a lack of research on building a unified system that can separate arbitrary sources via a single model. Second, most previous systems require clean source data to train a separator, while clean source data are scarce. Third, there is a lack of USS system that can automatically detect and separate active sound classes in a hierarchical level. To use large-scale weakly labeled/unlabeled audio data for audio source separation, we propose a universal audio source separation framework containing: 1) an audio tagging model trained on weakly labeled data as a query net; and 2) a conditional source separation model that takes query net outputs as conditions to separate arbitrary sound sources. We investigate various query nets, source separation models, and training strategies and propose a hierarchical USS strategy to automatically detect and separate sound classes from the AudioSet ontology. By solely leveraging the weakly labelled AudioSet, our USS system is successful in separating a wide variety of sound classes, including sound event separation, music source separation, and speech enhancement. The USS system achieves an average signal-to-distortion ratio improvement (SDRi) of 5.57 dB over 527 sound classes of AudioSet; 10.57 dB on the DCASE 2018 Task 2 dataset; 8.12 dB on the MUSDB18 dataset; an SDRi of 7.28 dB on the Slakh2100 dataset; and an SSNR of 9.00 dB on the voicebank-demand dataset. We release the source code at https://github.com/bytedance/uss
Contrastive learning has shown remarkable success in the field of multimodal representation learning. In this paper, we propose a pipeline of contrastive language-audio pretraining to develop an audio representation by combining audio data with natural language descriptions. To accomplish this target, we first release LAION-Audio-630K, a large collection of 633,526 audio-text pairs from different data sources. Second, we construct a contrastive language-audio pretraining model by considering different audio encoders and text encoders. We incorporate the feature fusion mechanism and keyword-to-caption augmentation into the model design to further enable the model to process audio inputs of variable lengths and enhance the performance. Third, we perform comprehensive experiments to evaluate our model across three tasks: text-to-audio retrieval, zero-shot audio classification, and supervised audio classification. The results demonstrate that our model achieves superior performance in text-to-audio retrieval task. In audio classification tasks, the model achieves state-of-the-art performance in the zero-shot setting and is able to obtain performance comparable to models' results in the non-zero-shot setting. LAION-Audio-630K and the proposed model are both available to the public.
Choral music separation refers to the task of extracting tracks of voice parts (e.g., soprano, alto, tenor, and bass) from mixed audio. The lack of datasets has impeded research on this topic as previous work has only been able to train and evaluate models on a few minutes of choral music data due to copyright issues and dataset collection difficulties. In this paper, we investigate the use of synthesized training data for the source separation task on real choral music. We make three contributions: first, we provide an automated pipeline for synthesizing choral music data from sampled instrument plugins within controllable options for instrument expressiveness. This produces an 8.2-hour-long choral music dataset from the JSB Chorales Dataset and one can easily synthesize additional data. Second, we conduct an experiment to evaluate multiple separation models on available choral music separation datasets from previous work. To the best of our knowledge, this is the first experiment to comprehensively evaluate choral music separation. Third, experiments demonstrate that the synthesized choral data is of sufficient quality to improve the model's performance on real choral music datasets. This provides additional experimental statistics and data support for the choral music separation study.