YYYi-Hsuan Yang

Yi-Hsuan Yang

*This is an algorithmically generated author record based on publicly available information.

Yi-Hsuan Yang has a total of 80 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Toward Generalizability to Tone and Content Variations in the Transcription of Amplifier Rendered Electric Guitar Audio

    by Yu-Hua Chen, Yuan-Chiao Cheng, Yen-Tung Yeh, Jui-Te Wu, Jyh-Shing Roger Jang, Yi-Hsuan Yang

    Electric guitar recordings pose unique challenges for automatic music transcription due to the rich tone-related variations arisen from the employed guitar amplifiers, cabinets, and effect pedals, which collectively alter the sound character the guitar produces. Transcription models trained on small datasets with a limited palette of guitar tones may not generalize well to unseen tones. Due to the scarcity of labeled data, however, little work has thoroughly studied the effect of tones in electric guitar transcription. In this paper, we present a prototype benchmark and evaluation protocol for electric guitar transcription, training our transcription models using up to 256 presets of commercialgrade amplifier-cabinet combinations with different gain ranges, and testing the models on an unseen set of 6 out-of-domain presets. Moreover, we propose a new Transformer-based transcription model named tone-informed hierarchical frequencytime Transformer (Ti-hFT) that incorporates representations of guitar tones as conditions to improve the model's adaptability to tone-related nuances. Experiments demonstrate the effectiveness of this tone-informed model over baselines and prior models, as well as the importance of increasing the tone and content variation of the training data for better generalizability.

  • Open Access

    PiCoGen: Generate Piano Covers with a Two-stage Approach

    by Chih-Pin Tan, Shuen-Huei Guan, Yi-Hsuan Yang

    Cover song generation stands out as a popular way of music making in the music-creative community. In this study, we introduce Piano Cover Generation (PiCoGen), a two-stage approach for automatic cover song generation that transcribes the melody line and chord progression of a song given its audio recording, and then uses the resulting lead sheet as the condition to generate a piano cover in the symbolic domain. This approach is advantageous in that it does not required paired data of covers and their original songs for training. Compared to an existing approach that demands such paired data, our evaluation shows that PiCoGen demonstrates competitive or even superior performance across songs of different musical genres.


  • Open Access

    MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Classification Tasks

    by Yi-Hui Chou, I-Chun Chen, Joann Ching, Chin-Jui Chang, Yi-Hsuan Yang

    This paper presents a benchmark study of MIDI-domain music classification using the mask language modeling approach of the Bidirectional Encoder Representations from Transformers (BERT). Specifically, with five public-domain datasets of single-track polyphonic piano MIDI files, we pre-train a 12-layer Transformer model using the BERT approach and fine-tune it for four downstream classification tasks. These include two note-level classification tasks---melody extraction and velocity prediction, and two sequence-level classification tasks---artist classification and emotion classification. Compared to strong recurrent neural network (RNN)-based baselines, the BERT approach does lead to higher classification accuracy, with less than 10 epochs of fine-tuning. Ablation studies further show that the pre-training remains effective even if the MIDI data of the downstream tasks are not seen during the pre-training stage, and that freezing the self-attention layers at the fine-tuning stage only slightly degrades the performance. For reproducibility, we share the weights of our pre-trained and fine-tuned models.


  • Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

    by Ching-Yu Chiu, Meinard Müller, Matthew E. P. Davies, Alvin Wen-Yu Su, Yi-Hsuan Yang

    To model the periodicity of beats, state-of-the-art beat tracking systems use “post-processing trackers” (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called “predominant local pulses” (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838).


  • Top Cited Papers

    MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer With One Transformer VAE

    by Shih-Lun Wu, Yi-Hsuan Yang

    Transformers and variational autoencoders (VAE) have been extensively employed for symbolic (e.g., MIDI) domain music generation. While the former boast an impressive capability in modeling long sequences, the latter allow users to willingly exert control over different parts (e.g., bars) of the music to be generated. In this paper, we are interested in bringing the two together to construct a single model that exhibits both strengths. The task is split into two steps. First, we equip Transformer decoders with the ability to accept segment-level, time-varying conditions during sequence generation. Subsequently, we combine the developed and tested in-attention decoder with a Transformer encoder, and train the resulting MuseMorphose model with the VAE objective to achieve style transfer of long pop piano pieces, in which users can specify musical attributes including rhythmic intensity and polyphony (i.e., harmonic fullness) they desire, down to the bar level. Experiments show that MuseMorphose outperforms recurrent neural network (RNN) based baselines on numerous widely-used metrics for style transfer tasks.


  • Open Access

    On Output Activation Functions for Adversarial Losses: A Theoretical Analysis via Variational Divergence Minimization and An Empirical Study on MNIST Classification

    by Hao-Wen Dong, Yi-Hsuan Yang

    Recent years have seen adversarial losses been applied to many fields. Their applications extend beyond the originally proposed generative modeling to conditional generative and discriminative settings. While prior work has proposed various output activation functions and regularization approaches, some open questions still remain unanswered. In this paper, we aim to study the following two research questions: 1) What types of output activation functions form a well-behaved adversarial loss? 2) How different combinations of output activation functions and regularization approaches perform empirically against one another? To answer the first question, we adopt the perspective of variational divergence minimization and consider an adversarial loss well-behaved if it behaves as a divergence-like measure between the data and model distributions. Using a generalized formulation for adversarial losses, we derive the necessary and sufficient conditions of a well-behaved adversarial loss. Our analysis reveals a large class of theoretically valid adversarial losses. For the second question, we propose a simple comparative framework for adversarial losses using discriminative adversarial networks. The proposed framework allows us to efficiently evaluate adversarial losses using a standard evaluation metric such as the classification accuracy. With the proposed framework, we evaluate a comprehensive set of 168 combinations of twelve output activation functions and fourteen regularization approaches on the handwritten digit classification problem to decouple their effects. Our empirical findings suggest that there is no single winning combination of output activation functions and regularization approaches across all settings. Our theoretical and empirical results may together serve as a reference for choosing or designing adversarial losses in future research.

  • An Analysis Method for Metric-Level Switching in Beat Tracking

    by Ching-Yu Chiu, Meinard Muller, Matthew E. P. Davies, Alvin Wen-Yu Su, Yi-Hsuan Yang

    For expressive music, the tempo may change over time, posing challenges to tracking the beats by an automatic model. The model may first tap to the correct tempo, but then may fail to adapt to a tempo change, or switch between several incorrect but perceptually plausible ones (e.g., half- or double-tempo). Existing evaluation metrics for beat tracking do not reflect such behaviors, as they typically assume a fixed relationship between the reference beats and estimated beats. In this letter, we propose a new performance analysis method, called annotation coverage ratio (ACR), that accounts for a variety of possible metric-level switching behaviors of beat trackers. The idea is to derive sequences of modified reference beats of all metrical levels for every two consecutive reference beats, and compare every sequence of modified reference beats to the subsequences of estimated beats. We show via experiments on three datasets of different genres the usefulness of ACR when being utilized alongside existing metrics, and discuss the new insights that can be gained.


  • Open Access

    A Benchmarking Initiative for Audio-Domain Music Generation Using the Freesound Loop Dataset

    by Tun-Min Hung, Bo-Yu Chen, Yen-Tung Yeh, Yi-Hsuan Yang

    This paper proposes a new benchmark task for generat-ing musical passages in the audio domain by using thedrum loops from the FreeSound Loop Dataset, which arepublicly re-distributable. Moreover, we use a larger col-lection of drum loops from Looperman to establish fourmodel-based objective metrics for evaluation, releasingthese metrics as a library for quantifying and facilitatingthe progress of musical audio generation. Under this eval-uation framework, we benchmark the performance of threerecent deep generative adversarial network (GAN) mod-els we customize to generate loops, including StyleGAN,StyleGAN2, and UNAGAN. We also report a subjectiveevaluation of these models. Our evaluation shows that theone based on StyleGAN2 performs the best in both objec-tive and subjective metrics.

  • Top Cited Papers

    Theme Transformer: Symbolic Music Generation With Theme-Conditioned Transformer

    by Yi-Jen Shih, Shih-Lun Wu, Frank Zalkow, Meinard Müller, Yi-Hsuan Yang

    Attention-based Transformer models have been increasingly employed for automatic music generation. To condition the generation process of such a model with a user-specified sequence, a popular approach is to take that conditioning sequence as a priming sequence and ask a Transformer decoder to generate a continuation. However, this prompt-based conditioning cannot guarantee that the conditioning sequence would develop or even simply repeat itself in the generated continuation. In this paper, we propose an alternative conditioning approach, called theme-based conditioning, that explicitly trains the Transformer to treat the conditioning sequence as a thematic material that has to manifest itself multiple times in its generation result. This is achieved with two main technical contributions. First, we propose a deep learning-based approach that uses contrastive representation learning and clustering to automatically retrieve thematic materials from music pieces in the training data. Second, we propose a novel gated parallel attention module to be used in a sequence-to-sequence (seq2seq) encoder/decoder architecture to more effectively account for a given conditioning thematic material in the generation process of the Transformer decoder. We report on objective and subjective evaluations of variants of the proposed Theme Transformer and the conventional prompt-based baseline, showing that our best model can generate, to some extent, polyphonic pop piano music with repetition and plausible variations of a given condition.


  • Open Access

    Neural Loop Combiner: Neural Network Models for Assessing the Compatibility of Loops

    by Bo-Yu Chen, Jordan B. L. Smith, Yi-Hsuan Yang

    Music producers who use loops may have access to thousands in loop libraries, but finding ones that are compatible is a time-consuming process; we hope to reduce this burden with automation. State-of-the-art systems for estimating compatibility, such as AutoMashUpper, are mostly rule-based and could be improved on with machine learn-ing. To train a model, we need a large set of loops with ground truth compatibility values. No such dataset exists, so we extract loops from existing music to obtain positive examples of compatible loops, and propose and compare various strategies for choosing negative examples. For re-producibility, we curate data from the Free Music Archive.Using this data, we investigate two types of model architectures for estimating the compatibility of loops: one based on a Siamese network, and the other a pure convolutional neural network (CNN). We conducted a user study in which participants rated the quality of the combinations suggested by each model, and found the CNN to outperform the Siamese network. Both model-based approaches outperformed the rule-based one. We have opened source the code for building the models and the dataset.