Search

Electric guitar tone modeling typically focuses on the non-linear transformation from clean to amplifier-rendered audio. Traditional methods rely on one-to-one mappings, incorporating device parameters into neural models to replicate specific amplifiers. However, these methods are limited by the need for specific training data. In this paper, we adapt a model based on the previous work, which leverages a tone embedding encoder and a feature wise linear modulation (FiLM) condition method. In this work, we altered conditioning method using a hypernetwork-based gated convolutional network (GCN) to generate audio that blends clean input with the tone characteristics of reference audio. By extending the training data to cover a wider variety of amplifier tones, our model is able to capture a broader range of tones. Additionally, we developed a real-time plugin to demonstrate the system's practical application, allowing users to experience its performance interactively. Our results indicate that the proposed system achieves superior tone modeling versatility compared to traditional methods., Comment: demo of the ISMIR paper

Mainstream zero-shot TTS production systems like Voicebox and Seed-TTS achieve human parity speech by leveraging Flow-matching and Diffusion models, respectively. Unfortunately, human-level audio synthesis leads to identity misuse and information security issues. Currently, many antispoofing models have been developed against deepfake audio. However, the efficacy of current state-of-the-art anti-spoofing models in countering audio synthesized by diffusion and flowmatching based TTS systems remains unknown. In this paper, we proposed the Diffusion and Flow-matching based Audio Deepfake (DFADD) dataset. The DFADD dataset collected the deepfake audio based on advanced diffusion and flowmatching TTS models. Additionally, we reveal that current anti-spoofing models lack sufficient robustness against highly human-like audio generated by diffusion and flow-matching TTS systems. The proposed DFADD dataset addresses this gap and provides a valuable resource for developing more resilient anti-spoofing models., Comment: Accepted by IEEE SLT 2024

Replicating analog device circuits through neural audio effect modeling has garnered increasing interest in recent years. Existing work has predominantly focused on a one-to-one emulation strategy, modeling specific devices individually. In this paper, we tackle the less-explored scenario of one-to-many emulation, utilizing conditioning mechanisms to emulate multiple guitar amplifiers through a single neural model. For condition representation, we use contrastive learning to build a tone embedding encoder that extracts style-related features of various amplifiers, leveraging a dataset of comprehensive amplifier settings. Targeting zero-shot application scenarios, we also examine various strategies for tone embedding representation, evaluating referenced tone embedding against two retrieval-based embedding methods for amplifiers unseen in the training time. Our findings showcase the efficacy and potential of the proposed methods in achieving versatile one-to-many amplifier modeling, contributing a foundational step towards zero-shot audio modeling applications., Comment: ISMIR 2024

Music source separation aims to separate polyphonic music into different types of sources. Most existing methods focus on enhancing the quality of separated results by using a larger model structure, rendering them unsuitable for deployment on edge devices. Moreover, these methods may produce low-quality output when the input duration is short, making them impractical for real-time applications. Therefore, the goal of this paper is to enhance a lightweight model, MMDenstNet, to strike a balance between separation quality and latency for real-time applications. Different directions of improvement are explored or proposed in this paper, including complex ideal ratio mask, self-attention, band-merge-split method, and feature look back. Source-to-distortion ratio, real-time factor, and optimal latency are employed to evaluate the performance. To align with our application requirements, the evaluation process in this paper focuses on the separation performance of the accompaniment part. Experimental results demonstrate that our improvement achieves low real-time factor and optimal latency while maintaining acceptable separation quality.

Recent years have seen increasing interest in applying deep learning methods to the modeling of guitar amplifiers or effect pedals. Existing methods are mainly based on the supervised approach, requiring temporally-aligned data pairs of unprocessed and rendered audio. However, this approach does not scale well, due to the complicated process involved in creating the data pairs. A very recent work done by Wright et al. has explored the potential of leveraging unpaired data for training, using a generative adversarial network (GAN)-based framework. This paper extends their work by using more advanced discriminators in the GAN, and using more unpaired data for training. Specifically, drawing inspiration from recent advancements in neural vocoders, we employ in our GAN-based model for guitar amplifier modeling two sets of discriminators, one based on multi-scale discriminator (MSD) and the other multi-period discriminator (MPD). Moreover, we experiment with adding unprocessed audio signals that do not have the corresponding rendered audio of a target tone to the training data, to see how much the GAN model benefits from the unpaired data. Our experiments show that the proposed two extensions contribute to the modeling of both low-gain and high-gain guitar amplifiers., Comment: Accepted to DAFx 2024

Automatic Speaker Verification (ASV), increasingly used in security-critical applications, faces vulnerabilities from rising adversarial attacks, with few effective defenses available. In this paper, we propose a neural codec-based adversarial sample detection method for ASV. The approach leverages the codec's ability to discard redundant perturbations and retain essential information. Specifically, we distinguish between genuine and adversarial samples by comparing ASV score differences between original and re-synthesized audio (by codec models). This comprehensive study explores all open-source neural codecs and their variant models for experiments. The Descript-audio-codec model stands out by delivering the highest detection rate among 15 neural codecs and surpassing seven prior state-of-the-art (SOTA) detection methods. Note that, our single-model method even outperforms a SOTA ensemble method by a large margin., Comment: Accepted by Interspeech 2024

Detecting singing voice deepfakes, or SingFake, involves determining the authenticity and copyright of a singing voice. Existing models for speech deepfake detection have struggled to adapt to unseen attacks in this unique singing voice domain of human vocalization. To bridge the gap, we present a groundbreaking SingGraph model. The model synergizes the capabilities of the MERT acoustic music understanding model for pitch and rhythm analysis with the wav2vec2.0 model for linguistic analysis of lyrics. Additionally, we advocate for using RawBoost and beat matching techniques grounded in music domain knowledge for singing voice augmentation, thereby enhancing SingFake detection performance. Our proposed method achieves new state-of-the-art (SOTA) results within the SingFake dataset, surpassing the previous SOTA model across three distinct scenarios: it improves EER relatively for seen singers by 13.2%, for unseen singers by 24.3%, and unseen singers using different codecs by 37.1%., Comment: Accepted by Interspeech 2024; Our code is available at https://github.com/xjchenGit/SingGraph.git

Speech emotion recognition (SER) is a pivotal technology for human-computer interaction systems. However, 80.77% of SER papers yield results that cannot be reproduced. We develop EMO-SUPERB, short for EMOtion Speech Universal PERformance Benchmark, which aims to enhance open-source initiatives for SER. EMO-SUPERB includes a user-friendly codebase to leverage 15 state-of-the-art speech self-supervised learning models (SSLMs) for exhaustive evaluation across six open-source SER datasets. EMO-SUPERB streamlines result sharing via an online leaderboard, fostering collaboration within a community-driven benchmark and thereby enhancing the development of SER. On average, 2.58% of annotations are annotated using natural language. SER relies on classification models and is unable to process natural languages, leading to the discarding of these valuable annotations. We prompt ChatGPT to mimic annotators, comprehend natural language annotations, and subsequently re-label the data. By utilizing labels generated by ChatGPT, we consistently achieve an average relative gain of 3.08% across all settings., Comment: webpage: https://emosuperb.github.io/

We present four main contributions to enhance the performance of Large Language Models (LLMs) in generating domain-specific code: (i) utilizing LLM-based data splitting and data renovation techniques to improve the semantic representation of embeddings' space; (ii) introducing the Chain of Density for Renovation Credibility (CoDRC), driven by LLMs, and the Adaptive Text Renovation (ATR) algorithm for assessing data renovation reliability; (iii) developing the Implicit Knowledge Expansion and Contemplation (IKEC) Prompt technique; and (iv) effectively refactoring existing scripts to generate new and high-quality scripts with LLMs. By using engineering simulation software RedHawk-SC as a case study, we demonstrate the effectiveness of our data pre-processing method for expanding and categorizing scripts. When combined with IKEC, these techniques enhance the Retrieval-Augmented Generation (RAG) method in retrieving more relevant information, ultimately achieving a 73.33% "Percentage of Correct Lines" for code generation problems in MapReduce applications.

The tasks of automatic lyrics transcription and lyrics alignment have witnessed significant performance improvements in the past few years. However, most of the previous works only focus on English in which large-scale datasets are available. In this paper, we address lyrics transcription and alignment of polyphonic Mandarin pop music in a low-resource setting. To deal with the data scarcity issue, we adapt pretrained Whisper model and fine-tune it on a monophonic Mandarin singing dataset. With the use of data augmentation and source separation model, results show that the proposed method achieves a character error rate of less than 18% on a Mandarin polyphonic dataset for lyrics transcription, and a mean absolute error of 0.071 seconds for lyrics alignment. Our results demonstrate the potential of adapting a pretrained speech model for lyrics transcription and alignment in low-resource scenarios., Comment: Accepted by ASRU 2023

Our research focuses on solving the zero-shot text classification problem in NLP, with a particular emphasis on innovative self-training strategies. To achieve this objective, we propose a novel self-training strategy that uses labels rather than text for training, significantly reducing the model's training time. Specifically, we use categories from Wikipedia as our training set and leverage the SBERT pre-trained model to establish positive correlations between pairs of categories within the same text, facilitating associative training. For new test datasets, we have improved the original self-training approach, eliminating the need for prior training and testing data from each target dataset. Instead, we adopt Wikipedia as a unified training dataset to better approximate the zero-shot scenario. This modification allows for rapid fine-tuning and inference across different datasets, greatly reducing the time required for self-training. Our experimental results demonstrate that this method can adapt the model to the target dataset within minutes. Compared to other BERT-based transformer models, our approach significantly reduces the amount of training data by training only on labels, not the actual text, and greatly improves training efficiency by utilizing a unified training set. Additionally, our method achieves state-of-the-art results on both the Yahoo Topic and AG News datasets.

This paper proposes to use both audio input and subject information to predict the personalized preference of two audio segments with the same content in different qualities. A siamese network is used to compare the inputs and predict the preference. Several different structures for each side of the siamese network are investigated, and an LDNet with PANNs' CNN6 as the encoder and a multi-layer perceptron block as the decoder outperforms a baseline model using only audio input the most, where the overall accuracy grows from 77.56% to 78.04%. Experimental results also show that using all the subject information, including age, gender, and the specifications of headphones or earphones, is more effective than using only a part of them.

Audio-visual synchronization aims to determine whether the mouth movements and speech in the video are synchronized. VocaLiST reaches state-of-the-art performance by incorporating multimodal Transformers to model audio-visual interact information. However, it requires high computing resources, making it impractical for real-world applications. This paper proposed an MTDVocaLiST model, which is trained by our proposed multimodal Transformer distillation (MTD) loss. MTD loss enables MTDVocaLiST model to deeply mimic the cross-attention distribution and value-relation in the Transformer of VocaLiST. Additionally, we harness uncertainty weighting to fully exploit the interaction information across all layers. Our proposed method is effective in two aspects: From the distillation method perspective, MTD loss outperforms other strong distillation baselines. From the distilled model's performance perspective: 1) MTDVocaLiST outperforms similar-size SOTA models, SyncNet, and Perfect Match models by 15.65% and 3.35%; 2) MTDVocaLiST reduces the model size of VocaLiST by 83.52%, yet still maintaining similar performance., Comment: Accepted by ICASSP 2024

Audio-visual active speaker detection (AVASD) is well-developed, and now is an indispensable front-end for several multi-modal applications. However, to the best of our knowledge, the adversarial robustness of AVASD models hasn't been investigated, not to mention the effective defense against such attacks. In this paper, we are the first to reveal the vulnerability of AVASD models under audio-only, visual-only, and audio-visual adversarial attacks through extensive experiments. What's more, we also propose a novel audio-visual interaction loss (AVIL) for making attackers difficult to find feasible adversarial examples under an allocated attack budget. The loss aims at pushing the inter-class embeddings to be dispersed, namely non-speech and speech clusters, sufficiently disentangled, and pulling the intra-class embeddings as close as possible to keep them compact. Experimental results show the AVIL outperforms the adversarial training by 33.14 mAP (%) under multi-modal attacks., Comment: Accepted by SLT 2022

The countermeasure (CM) model is developed to protect ASV systems from spoof attacks and prevent resulting personal information leakage in Automatic Speaker Verification (ASV) system. Based on practicality and security considerations, the CM model is usually deployed on edge devices, which have more limited computing resources and storage space than cloud-based systems, confining the model size under a limitation. To better trade off the CM model sizes and performance, we proposed an adversarial speaker distillation method, which is an improved version of knowledge distillation method combined with generalized end-to-end (GE2E) pre-training and adversarial fine-tuning. In the evaluation phase of the ASVspoof 2021 Logical Access task, our proposed adversarial speaker distillation ResNetSE (ASD-ResNetSE) model reaches 0.2695 min t-DCF and 3.54% EER. ASD-ResNetSE only used 22.5% of parameters and 19.4% of multiply and accumulate operands of ResNetSE model., Comment: Accepted by ISCA SPSC 2022

In this paper, we propose a new dataset named EGDB, that con-tains transcriptions of the electric guitar performance of 240 tab-latures rendered with different tones. Moreover, we benchmark theperformance of two well-known transcription models proposed orig-inally for the piano on this dataset, along with a multi-loss Trans-former model that we newly propose. Our evaluation on this datasetand a separate set of real-world recordings demonstrate the influenceof timbre on the accuracy of guitar sheet transcription, the potentialof using multiple losses for Transformers, as well as the room forfurther improvement for this task., Comment: to be published at ICASSP 2022

Due to the rapid development of deep learning, we can now successfully separate singing voice from mono audio music. However, this separation can only extract human voices from other musical instruments, which is undesirable for karaoke content generation applications that only require the separation of lead singers. For this karaoke application, we need to separate the music containing male and female duets into two vocals, or extract a single lead vocal from the music containing vocal harmony. For this reason, we propose in this article to use a singer separation system, which generates karaoke content for one or two separated lead singers. In particular, we introduced three models for the singer separation task and designed an automatic model selection scheme to distinguish how many lead singers are in the song. We also collected a large enough data set, MIR-SingerSeparation, which has been publicly released to advance the frontier of this research. Our singer separation is most suitable for sentimental ballads and can be directly applied to karaoke content generation. As far as we know, this is the first singer-separation work for real-world karaoke applications.

For a data holder, such as a hospital or a government entity, who has a privately held collection of personal data, in which the revealing and/or processing of the personal identifiable data is restricted and prohibited by law. Then, "how can we ensure the data holder does conceal the identity of each individual in the imagery of personal data while still preserving certain useful aspects of the data after de-identification?" becomes a challenge issue. In this work, we propose an approach towards high-resolution facial image de-identification, called k-Same-Siamese-GAN, which leverages the k-Same-Anonymity mechanism, the Generative Adversarial Network, and the hyperparameter tuning methods. Moreover, to speed up model training and reduce memory consumption, the mixed precision training technique is also applied to make kSS-GAN provide guarantees regarding privacy protection on close-form identities and be trained much more efficiently as well. Finally, to validate its applicability, the proposed work has been applied to actual datasets - RafD and CelebA for performance testing. Besides protecting privacy of high-resolution facial images, the proposed system is also justified for its ability in automating parameter tuning and breaking through the limitation of the number of adjustable parameters.

In this paper, we introduce a novel attentional similarity module for the problem of few-shot sound recognition. Given a few examples of an unseen sound event, a classifier must be quickly adapted to recognize the new sound event without much fine-tuning. The proposed attentional similarity module can be plugged into any metric-based learning method for few-shot learning, allowing the resulting model to especially match related short sound events. Extensive experiments on two datasets shows that the proposed module consistently improves the performance of five different metric-based learning methods for few-shot sound recognition. The relative improvement ranges from +4.1% to +7.7% for 5-shot 5-way accuracy for the ESC-50 dataset, and from +2.1% to +6.5% for noiseESC-50. Qualitative results demonstrate that our method contributes in particular to the recognition of transient sound events., Comment: This is a pre-print version of an ICASSP 2019 paper

Can we make a famous rap singer like Eminem sing whatever our favorite song? Singing style transfer attempts to make this possible, by replacing the vocal of a song from the source singer to the target singer. This paper presents a method that learns from unpaired data for singing style transfer using generative adversarial networks., Comment: 3 pages, 3 figures, demo website: http://mirlab.org/users/haley.wu/cybegan

Vector-valued neural learning has emerged as a promising direction in deep learning recently. Traditionally, training data for neural networks (NNs) are formulated as a vector of scalars; however, its performance may not be optimal since associations among adjacent scalars are not modeled. In this paper, we propose a new vector neural architecture called the Arbitrary BIlinear Product Neural Network (ABIPNN), which processes information as vectors in each neuron, and the feedforward projections are defined using arbitrary bilinear products. Such bilinear products can include circular convolution, seven-dimensional vector product, skew circular convolution, reversed- time circular convolution, or other new products not seen in previous work. As a proof-of-concept, we apply our proposed network to multispectral image denoising and singing voice sepa- ration. Experimental results show that ABIPNN gains substantial improvements when compared to conventional NNs, suggesting that associations are learned during training., Comment: 14 pages, 8 figures, 3 tables

Separating two sources from an audio mixture is an important task with many applications. It is a challenging problem since only one signal channel is available for analysis. In this paper, we propose a novel framework for singing voice separation using the generative adversarial network (GAN) with a time-frequency masking function. The mixture spectra is considered to be a distribution and is mapped to the clean spectra which is also considered a distribtution. The approximation of distributions between mixture spectra and clean spectra is performed during the adversarial training process. In contrast with current deep learning approaches for source separation, the parameters of the proposed framework are first initialized in a supervised setting and then optimized by the training procedure of GAN in an unsupervised setting. Experimental results on three datasets (MIR-1K, iKala and DSD100) show that performance can be improved by the proposed framework consisting of conventional networks., Comment: 5 pages, 4 figures, 1 table. Demo website: http://mirlab.org/demo/svsgan

This paper presents a new technique for the design of approximate reasoning based controllers for dynamic physical systems with interacting goals. In this approach, goals are achieved based on a hierarchy defined by a control knowledge base and remain highly interactive during the execution of the control task. The approach has been implemented in a rule-based computer program which is used in conjunction with a prototype hardware system to solve the cart-pole balancing problem in real-time. It provides a complementary approach to the conventional analytical control methodology, and is of substantial use where a precise mathematical model of the process being controlled is not available., Comment: Appears in Proceedings of the Sixth Conference on Uncertainty in Artificial Intelligence (UAI1990)