arXiv subjects

Kyogu Lee

Publications and source records attributed to Kyogu Lee.

At least 55 records · Page 3Linked to original sources

arXiv2024

Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation

Transformer encoder with connectionist temporal classification (CTC) framework is widely used for automatic speech recognition (ASR). However, knowledge distillation (KD) for ASR displays a problem of disagreement between teacher-student models in frame-level alignment which ultimately hinders it from improving the student model's performance. In order to resolve this problem, this paper introduces a self-knowledge distillation (SKD) method that guides the frame-level alignment during the training time. In contrast to the conventional method using separate teacher and student models, this study introduces a simple and effective method sharing encoder layers and applying the sub-model as the student model. Overall, our approach is effective in improving both the resource efficiency as well as performance. We also conducted an experimental analysis of the spike timings to illustrate that the proposed method improves performance by reducing the alignment disagreement.

eess.AS↗

arXiv2024

Distance Sampling-based Paraphraser Leveraging ChatGPT for Text Data Manipulation

There has been growing interest in audio-language retrieval research, where the objective is to establish the correlation between audio and text modalities. However, most audio-text paired datasets often lack rich expression of the text data compared to the audio samples. One of the significant challenges facing audio-text datasets is the presence of similar or identical captions despite different audio samples. Therefore, under many-to-one mapping conditions, audio-text datasets lead to poor performance of retrieval tasks. In this paper, we propose a novel approach to tackle the data imbalance problem in audio-language retrieval task. To overcome the limitation, we introduce a method that employs a distance sampling-based paraphraser leveraging ChatGPT, utilizing distance function to generate a controllable distribution of manipulated text data. For a set of sentences with the same context, the distance is used to calculate a degree of manipulation for any two sentences, and ChatGPT's few-shot prompting is performed using a text cluster with a similar distance defined by the Jaccard similarity. Therefore, ChatGPT, when applied to few-shot prompting with text clusters, can adjust the diversity of the manipulated text based on the distance. The proposed approach is shown to significantly enhance performance in audio-text retrieval, outperforming conventional text augmentation techniques.

cs.IR↗

arXiv2024

Removing Speaker Information from Speech Representation using Variable-Length Soft Pooling

Recently, there have been efforts to encode the linguistic information of speech using a self-supervised framework for speech synthesis. However, predicting representations from surrounding representations can inadvertently entangle speaker information in the speech representation. This paper aims to remove speaker information by exploiting the structured nature of speech, composed of discrete units like phonemes with clear boundaries. A neural network predicts these boundaries, enabling variable-length pooling for event-based representation extraction instead of fixed-rate methods. The boundary predictor outputs a probability for the boundary between 0 and 1, making pooling soft. The model is trained to minimize the difference with the pooled representation of the data augmented by time-stretch and pitch-shift. To confirm that the learned representation includes contents information but is independent of speaker information, the model was evaluated with libri-light's phonetic ABX task and SUPERB's speaker identification task.

cs.SD↗

arXiv2024

Learning Semantic Information from Raw Audio Signal Using Both Contextual and Phonetic Representations

We propose a framework to learn semantics from raw audio signals using two types of representations, encoding contextual and phonetic information respectively. Specifically, we introduce a speech-to-unit processing pipeline that captures two types of representations with different time resolutions. For the language model, we adopt a dual-channel architecture to incorporate both types of representation. We also present new training objectives, masked context reconstruction and masked context prediction, that push models to learn semantics effectively. Experiments on the sSIMI metric of Zero Resource Speech Benchmark 2021 and Fluent Speech Command dataset show our framework learns semantics better than models trained with only one type of representation.

eess.AS↗

arXiv2024

Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training

Music auto-tagging is crucial for enhancing music discovery and recommendation. Existing models in Music Information Retrieval (MIR) struggle with real-world noise such as environmental and speech sounds in multimedia content. This study proposes a method inspired by speech-related tasks to enhance music auto-tagging performance in noisy settings. The approach integrates Domain Adversarial Training (DAT) into the music domain, enabling robust music representations that withstand noise. Unlike previous research, this approach involves an additional pretraining phase for the domain classifier, to avoid performance degradation in the subsequent phase. Adding various synthesized noisy music data improves the model's generalization across different noise levels. The proposed architecture demonstrates enhanced performance in music auto-tagging by effectively utilizing unlabeled noisy music data. Additional experiments with supplementary unlabeled data further improves the model's performance, underscoring its robust generalization capabilities and broad applicability.

cs.SD↗

arXiv2024

String Sound Synthesizer on GPU-accelerated Finite Difference Scheme

This paper introduces a nonlinear string sound synthesizer, based on a finite difference simulation of the dynamic behavior of strings under various excitations. The presented synthesizer features a versatile string simulation engine capable of stochastic parameterization, encompassing fundamental frequency modulation, stiffness, tension, frequency-dependent loss, and excitation control. This open-source physical model simulator not only benefits the audio signal processing community but also contributes to the burgeoning field of neural network-based audio synthesis by serving as a novel dataset construction tool. Implemented in PyTorch, this synthesizer offers flexibility, facilitating both CPU and GPU utilization, thereby enhancing its applicability as a simulator. GPU utilization expedites computation by parallelizing operations across spatial and batch dimensions, further enhancing its utility as a data generator.

cs.SD↗

arXiv2024

DDD: A Perceptually Superior Low-Response-Time DNN-based Declipper

Clipping is a common nonlinear distortion that occurs whenever the input or output of an audio system exceeds the supported range. This phenomenon undermines not only the perception of speech quality but also downstream processes utilizing the disrupted signal. Therefore, a real-time-capable, robust, and low-response-time method for speech declipping (SD) is desired. In this work, we introduce DDD (Demucs-Discriminator-Declipper), a real-time-capable speech-declipping deep neural network (DNN) that requires less response time by design. We first observe that a previously untested real-time-capable DNN model, Demucs, exhibits a reasonable declipping performance. Then we utilize adversarial learning objectives to increase the perceptual quality of output speech without additional inference overhead. Subjective evaluations on harshly clipped speech shows that DDD outperforms the baselines by a wide margin in terms of speech quality. We perform detailed waveform and spectral analyses to gain an insight into the output behavior of DDD in comparison to the baselines. Finally, our streaming simulations also show that DDD is capable of sub-decisecond mean response times, outperforming the state-of-the-art DNN approach by a factor of six.

eess.AS↗

arXiv2023

Combinatorial music generation model with song structure graph analysis

In this work, we propose a symbolic music generation model with the song structure graph analysis network. We construct a graph that uses information such as note sequence and instrument as node features, while the correlation between note sequences acts as the edge feature. We trained a Graph Neural Network to obtain node representation in the graph, then we use node representation as input of Unet to generate CONLON pianoroll image latent. The outcomes of our experimental results show that the proposed model can generate a comprehensive form of music. Our approach represents a promising and innovative method for symbolic music generation and holds potential applications in various fields in Music Information Retreival, including music composition, music classification, and music inpainting systems.

cs.SD↗

arXiv2023

Beat-Aligned Spectrogram-to-Sequence Generation of Rhythm-Game Charts

In the heart of "rhythm games" - games where players must perform actions in sync with a piece of music - are "charts", the directives to be given to players. We newly formulate chart generation as a sequence generation task and train a Transformer using a large dataset. We also introduce tempo-informed preprocessing and training procedures, some of which are suggested to be integral for a successful training. Our model is found to outperform the baselines on a large dataset, and is also found to benefit from pretraining and finetuning.

cs.LG↗

arXiv2023

Yet Another Generative Model For Room Impulse Response Estimation

Recent neural room impulse response (RIR) estimators typically comprise an encoder for reference audio analysis and a generator for RIR synthesis. Especially, it is the performance of the generator that directly influences the overall estimation quality. In this context, we explore an alternate generator architecture for improved performance. We first train an autoencoder with residual quantization to learn a discrete latent token space, where each token represents a small time-frequency patch of the RIR. Then, we cast the RIR estimation problem as a reference-conditioned autoregressive token generation task, employing transformer variants that operate across frequency, time, and quantization depth axes. This way, we address the standard blind estimation task and additional acoustic matching problem, which aims to find an RIR that matches the source signal to the target signal's reverberation characteristics. Experimental results show that our system is preferable to other baselines across various evaluation metrics.

cs.SD↗

arXiv2023

Exploiting Time-Frequency Conformers for Music Audio Enhancement

With the proliferation of video platforms on the internet, recording musical performances by mobile devices has become commonplace. However, these recordings often suffer from degradation such as noise and reverberation, which negatively impact the listening experience. Consequently, the necessity for music audio enhancement (referred to as music enhancement from this point onward), involving the transformation of degraded audio recordings into pristine high-quality music, has surged to augment the auditory experience. To address this issue, we propose a music enhancement system based on the Conformer architecture that has demonstrated outstanding performance in speech enhancement tasks. Our approach explores the attention mechanisms of the Conformer and examines their performance to discover the best approach for the music enhancement task. Our experimental results show that our proposed model achieves state-of-the-art performance on single-stem music enhancement. Furthermore, our system can perform general music enhancement with multi-track mixtures, which has not been examined in previous work.

cs.SD↗

arXiv2023

Towards a New Interface for Music Listening: A User Experience Study on YouTube

In light of the enduring success of music streaming services, it is noteworthy that an increasing number of users are positively gravitating toward YouTube as their preferred platform for listening to music. YouTube differs from typical music streaming services in that they provide a diverse range of music-related videos as well as soundtracks. However, despite the increasing popularity of using YouTube as a platform for music consumption, there is still a lack of comprehensive research on this phenomenon. As independent researchers unaffiliated with YouTube, we conducted semi-structured interviews with 27 users who listen to music through YouTube more than three times a week to investigate its usability and interface satisfaction. Our qualitative analysis found that YouTube has five main meanings for users as a music streaming service: 1) exploring musical diversity, 2) sharing unique playlists, 3) providing visual satisfaction, 4) facilitating user interaction, and 5) allowing free and easy access. We also propose wireframes of a video streaming service for better audio-visual music listening in two stages: search and listening. By these wireframes, we offer practical solutions to enhance user satisfaction with YouTube for music listening. These findings have wider implications beyond YouTube and could inform enhancements in other music streaming services as well.

cs.HC↗

arXiv2023

Self-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data

Music source separation (MSS) faces challenges due to the limited availability of correctly-labeled individual instrument tracks. With the push to acquire larger datasets to improve MSS performance, the inevitability of encountering mislabeled individual instrument tracks becomes a significant challenge to address. This paper introduces an automated technique for refining the labels in a partially mislabeled dataset. Our proposed self-refining technique, employed with a noisy-labeled dataset, results in only a 1% accuracy degradation in multi-label instrument recognition compared to a classifier trained on a clean-labeled dataset. The study demonstrates the importance of refining noisy-labeled data in MSS model training and shows that utilizing the refined dataset leads to comparable results derived from a clean-labeled dataset. Notably, upon only access to a noisy dataset, MSS models trained on a self-refined dataset even outperform those trained on a dataset refined with a classifier trained on clean labels.

eess.AS↗

arXiv2023

Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test

Automatic speech recognition systems based on deep learning are mainly trained under empirical risk minimization (ERM). Since ERM utilizes the averaged performance on the data samples regardless of a group such as healthy or dysarthric speakers, ASR systems are unaware of the performance disparities across the groups. This results in biased ASR systems whose performance differences among groups are severe. In this study, we aim to improve the ASR system in terms of group robustness for dysarthric speakers. To achieve our goal, we present a novel approach, sample reweighting with sample affinity test (Re-SAT). Re-SAT systematically measures the debiasing helpfulness of the given data sample and then mitigates the bias by debiasing helpfulness-based sample reweighting. Experimental results demonstrate that Re-SAT contributes to improved ASR performance on dysarthric speech without performance degradation on healthy speech.

eess.AS↗

arXiv2023

Semi-supervised learning for continuous emotional intensity controllable speech synthesis with disentangled representations

Recent text-to-speech models have reached the level of generating natural speech similar to what humans say. But there still have limitations in terms of expressiveness. The existing emotional speech synthesis models have shown controllability using interpolated features with scaling parameters in emotional latent space. However, the emotional latent space generated from the existing models is difficult to control the continuous emotional intensity because of the entanglement of features like emotions, speakers, etc. In this paper, we propose a novel method to control the continuous intensity of emotions using semi-supervised learning. The model learns emotions of intermediate intensity using pseudo-labels generated from phoneme-level sequences of speech information. An embedding space built from the proposed model satisfies the uniform grid geometry with an emotional basis. The experimental results showed that the proposed method was superior in controllability and naturalness.

eess.AS↗

arXiv2023

Exploring Train and Test-Time Augmentations for Audio-Language Learning

In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augmentation methods at not only train-time but also test-time and find out that proper data augmentation can lead to substantial improvements. Specifically, applying our proposed audio-language paired augmentation PairMix, which is the first multi-modal audio-language augmentation method, outperforms the baselines for both automated audio captioning and audio-text retrieval tasks. To fully take advantage of data augmentation, we also present multi-level test-time augmentation (Multi-TTA) for the test-time. We successfully incorporate the two proposed methods and uni-modal augmentations and achieve 47.5 SPIDEr on audio captioning, which is an 18.2% relative increase over the baseline. In audio-text retrieval, the proposed methods also show an improvement in performance as well.

cs.SD↗

arXiv2023

Blind Estimation of Audio Processing Graph

Musicians and audio engineers sculpt and transform their sounds by connecting multiple processors, forming an audio processing graph. However, most deep-learning methods overlook this real-world practice and assume fixed graph settings. To bridge this gap, we develop a system that reconstructs the entire graph from a given reference audio. We first generate a realistic graph-reference pair dataset and train a simple blind estimation system composed of a convolutional reference encoder and a transformer-based graph decoder. We apply our model to singing voice effects and drum mixing estimation tasks. Evaluation results show that our method can reconstruct complex signal routings, including multi-band processing and sidechaining.

cs.SD↗

arXiv2023

MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separation

Separation of multiple singing voices into each voice is a rarely studied area in music source separation research. The absence of a benchmark dataset has hindered its progress. In this paper, we present an evaluation dataset and provide baseline studies for multiple singing voices separation. First, we introduce MedleyVox, an evaluation dataset for multiple singing voices separation. We specify the problem definition in this dataset by categorizing it into i) unison, ii) duet, iii) main vs. rest, and iv) N-singing separation. Second, to overcome the absence of existing multi-singing datasets for a training purpose, we present a strategy for construction of multiple singing mixtures using various single-singing datasets. Third, we propose the improved super-resolution network (iSRNet), which greatly enhances initial estimates of separation networks. Jointly trained with the Conv-TasNet and the multi-singing mixture construction strategy, the proposed iSRNet achieved comparable performance to ideal time-frequency masks on duet and unison subsets of MedleyVox. Audio samples, the dataset, and codes are available on our website (https://github.com/jeonchangbin49/MedleyVox).

cs.SD↗