arXiv subjects

Liping Chen

Publications and source records attributed to Liping Chen.

At least 37 records · Page 2Linked to original sources

arXiv2024

CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder

Singing Voice Synthesis (SVS) aims to generate singing voices of high fidelity and expressiveness. Conventional SVS systems usually utilize an acoustic model to transform a music score into acoustic features, followed by a vocoder to reconstruct the singing voice. It was recently shown that end-to-end modeling is effective in the fields of SVS and Text to Speech (TTS). In this work, we thus present a fully end-to-end SVS method together with a chunkwise streaming inference to address the latency issue for practical usages. Note that this is the first attempt to fully implement end-to-end streaming audio synthesis using latent representations in VAE. We have made specific improvements to enhance the performance of streaming SVS using latent representations. Experimental results demonstrate that the proposed method achieves synthesized audio with high expressiveness and pitch accuracy in both streaming SVS and TTS tasks.

eess.AS↗

arXiv2024

On the Generation and Removal of Speaker Adversarial Perturbation for Voice-Privacy Protection

Neural networks are commonly known to be vulnerable to adversarial attacks mounted through subtle perturbation on the input data. Recent development in voice-privacy protection has shown the positive use cases of the same technique to conceal speaker's voice attribute with additive perturbation signal generated by an adversarial network. This paper examines the reversibility property where an entity generating the adversarial perturbations is authorized to remove them and restore original speech (e.g., the speaker him/herself). A similar technique could also be used by an investigator to deanonymize a voice-protected speech to restore criminals' identities in security and forensic analysis. In this setting, the perturbation generative module is assumed to be known in the removal process. To this end, a joint training of perturbation generation and removal modules is proposed. Experimental results on the LibriSpeech dataset demonstrated that the subtle perturbations added to the original speech can be predicted from the anonymized speech while achieving the goal of privacy protection. By removing these perturbations from the anonymized sample, the original speech can be restored. Audio samples can be found in \url{https://voiceprivacy.github.io/Perturbation-Generation-Removal/}.

cs.SD↗

arXiv2024

Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embedding

Voice anonymization has been developed as a technique for preserving privacy by replacing the speaker's voice in a speech signal with that of a pseudo-speaker, thereby obscuring the original voice attributes from machine recognition and human perception. In this paper, we focus on altering the voice attributes against machine recognition while retaining human perception. We referred to this as the asynchronous voice anonymization. To this end, a speech generation framework incorporating a speaker disentanglement mechanism is employed to generate the anonymized speech. The speaker attributes are altered through adversarial perturbation applied on the speaker embedding, while human perception is preserved by controlling the intensity of perturbation. Experiments conducted on the LibriSpeech dataset showed that the speaker attributes were obscured with their human perception preserved for 60.71% of the processed utterances.

cs.SD↗

arXiv2024

SiFiSinger: A High-Fidelity End-to-End Singing Voice Synthesizer based on Source-filter Model

This paper presents an advanced end-to-end singing voice synthesis (SVS) system based on the source-filter mechanism that directly translates lyrical and melodic cues into expressive and high-fidelity human-like singing. Similarly to VISinger 2, the proposed system also utilizes training paradigms evolved from VITS and incorporates elements like the fundamental pitch (F0) predictor and waveform generation decoder. To address the issue that the coupling of mel-spectrogram features with F0 information may introduce errors during F0 prediction, we consider two strategies. Firstly, we leverage mel-cepstrum (mcep) features to decouple the intertwined mel-spectrogram and F0 characteristics. Secondly, inspired by the neural source-filter models, we introduce source excitation signals as the representation of F0 in the SVS system, aiming to capture pitch nuances more accurately. Meanwhile, differentiable mcep and F0 losses are employed as the waveform decoder supervision to fortify the prediction accuracy of speech envelope and pitch in the generated speech. Experiments on the Opencpop dataset demonstrate efficacy of the proposed model in synthesis quality and intonation accuracy.

eess.AS↗

arXiv2024

Design and Control of a Novel Six-Degree-of-Freedom Hybrid Robotic Arm

Robotic arms are key components in fruit-harvesting robots. In agricultural settings, conventional serial or parallel robotic arms often fall short in meeting the demands for a large workspace, rapid movement, enhanced capability of obstacle avoidance and affordability. This study proposes a novel hybrid six-degree-of-freedom (DoF) robotic arm that combines the advantages of parallel and serial mechanisms. Inspired by yoga, we designed two sliders capable of moving independently along a single rail, acting as two feet. These sliders are interconnected with linkages and a meshed-gear set, allowing the parallel mechanism to lower itself and perform a split to pass under obstacles. This unique feature allows the arm to avoid obstacles such as pipes, tables and beams typically found in greenhouses. Integrated with serially mounted joints, the patented hybrid arm is able to maintain the end's pose even when it moves with a mobile platform, facilitating fruit picking with the optimal pose in dynamic conditions. Moreover, the hybrid arm's workspace is substantially larger, being almost three times the volume of UR3 serial arms and fourteen times that of the ABB IRB parallel arms. Experiments show that the repeatability errors are 0.017 mm, 0.03 mm and 0.109 mm for the two sliders and the arm's end, respectively, providing sufficient precision for agricultural robots.

cs.RO↗

arXiv2024

Refining Self-Supervised Learnt Speech Representation using Brain Activations

It was shown in literature that speech representations extracted by self-supervised pre-trained models exhibit similarities with brain activations of human for speech perception and fine-tuning speech representation models on downstream tasks can further improve the similarity. However, it still remains unclear if this similarity can be used to optimize the pre-trained speech models. In this work, we therefore propose to use the brain activations recorded by fMRI to refine the often-used wav2vec2.0 model by aligning model representations toward human neural responses. Experimental results on SUPERB reveal that this operation is beneficial for several downstream tasks, e.g., speaker verification, automatic speech recognition, intent classification.One can then consider the proposed method as a new alternative to improve self-supervised speech models.

eess.AS↗

arXiv2024

LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer Guidance

Any-to-any singing voice conversion (SVC) is an interesting audio editing technique, aiming to convert the singing voice of one singer into that of another, given only a few seconds of singing data. However, during the conversion process, the issue of timbre leakage is inevitable: the converted singing voice still sounds like the original singer's voice. To tackle this, we propose a latent diffusion model for SVC (LDM-SVC) in this work, which attempts to perform SVC in the latent space using an LDM. We pretrain a variational autoencoder structure using the noted open-source So-VITS-SVC project based on the VITS framework, which is then used for the LDM training. Besides, we propose a singer guidance training method based on classifier-free guidance to further suppress the timbre of the original singer. Experimental results show the superiority of the proposed method over previous works in both subjective and objective evaluations of timbre similarity.

eess.AS↗

arXiv2024

Adversarial speech for voice privacy protection from Personalized Speech generation

The rapid progress in personalized speech generation technology, including personalized text-to-speech (TTS) and voice conversion (VC), poses a challenge in distinguishing between generated and real speech for human listeners, resulting in an urgent demand in protecting speakers' voices from malicious misuse. In this regard, we propose a speaker protection method based on adversarial attacks. The proposed method perturbs speech signals by minimally altering the original speech while rendering downstream speech generation models unable to accurately generate the voice of the target speaker. For validation, we employ the open-source pre-trained YourTTS model for speech generation and protect the target speaker's speech in the white-box scenario. Automatic speaker verification (ASV) evaluations were carried out on the generated speech as the assessment of the voice protection capability. Our experimental results show that we successfully perturbed the speaker encoder of the YourTTS model using the gradient-based I-FGSM adversarial perturbation method. Furthermore, the adversarial perturbation is effective in preventing the YourTTS model from generating the speech of the target speaker. Audio samples can be found in https://voiceprivacy.github.io/Adeversarial-Speech-with-YourTTS.

eess.AS↗

arXiv2022

Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation

Direct speech-to-speech translation (S2ST) is an attractive research topic with many advantages compared to cascaded S2ST. However, direct S2ST suffers from the data scarcity problem because the corpora from speech of the source language to speech of the target language are very rare. To address this issue, we propose in this paper a Speech2S model, which is jointly pre-trained with unpaired speech and bilingual text data for direct speech-to-speech translation tasks. By effectively leveraging the paired text data, Speech2S is capable of modeling the cross-lingual speech conversion from source to target language. We verify the performance of the proposed Speech2S on Europarl-ST and VoxPopuli datasets. Experimental results demonstrate that Speech2S gets an improvement of about 5 BLEU scores compared to encoder-only pre-training models, and achieves a competitive or even better performance than existing state-of-the-art models1.

cs.SD↗

arXiv2022

An Evolutionary Note on Smart City Development in China

In response to challenges posed by urbanization, David Bollier from the University of Southern California raised a new idea for city planning: a comprehensive network and applications of information technologies. IBM later echoed the idea and initiated its Smart Planet vision in 2008. After that, the smart city concept was quickly adopted by major cities throughout the world, and it has gradually evolved into a strategic choice by ambitious cities. This paper looks into the smart city trend by reviewing how the concept of smart city was proposed and what the essence of a smart city is. More specifically, the driving forces of the smart city development in China are investigated, and the key differences of smart cities between China and other countries are summarized. Finally, four big challenges to build future smart cities are discussed.

cs.CY↗

arXiv2021

Hierarchical Structural Analysis Method for Complex Equation-oriented Models

Structural analysis is a method for verifying equation-oriented models in the design of industrial systems. Existing structural analysis methods need flattening of the hierarchical models into an equation system for analysis. However, the large-scale equations in complex models make structural analysis difficult. Aimed to address the issue, this study proposes a hierarchical structural analysis method by exploring the relationship between the singularities of the hierarchical equation-oriented model and its components. This method obtains the singularity of a hierarchical equation-oriented model by analyzing a dummy model constructed with the parts from the decomposing results of its components. Based on this, the structural singularity of a complex model can be obtained by layer-by-layer analysis according to their natural hierarchy. The hierarchical structural analysis method can reduce the equation scale in each analysis and achieve efficient structural analysis of very complex models. This method can be adaptively applied to nonlinear-algebraic and differential-algebraic equation models. The main algorithms, application cases and comparison with the existing methods are present in this paper. The complexity analysis results show the enhanced efficiency of the proposed method in the structural analysis of complex equation-oriented models. Compared with the existing methods, the time complexity of the proposed method is improved significantly.

cs.OH↗

arXiv2021

Speech BERT Embedding For Improving Prosody in Neural TTS

This paper presents a speech BERT model to extract embedded prosody information in speech segments for improving the prosody of synthesized speech in neural text-to-speech (TTS). As a pre-trained model, it can learn prosody attributes from a large amount of speech data, which can utilize more data than the original training data used by the target TTS. The embedding is extracted from the previous segment of a fixed length in the proposed BERT. The extracted embedding is then used together with the mel-spectrogram to predict the following segment in the TTS decoder. Experimental results obtained by the Transformer TTS show that the proposed BERT can extract fine-grained, segment-level prosody, which is complementary to utterance-level prosody to improve the final prosody of the TTS speech. The objective distortions measured on a single speaker TTS are reduced between the generated speech and original recordings. Subjective listening tests also show that the proposed approach is favorably preferred over the TTS without the BERT prosody embedding module, for both in-domain and out-of-domain applications. For Microsoft professional, single/multiple speakers and the LJ Speaker in the public database, subjective preference is similarly confirmed with the new BERT prosody embedding. TTS demo audio samples are in https://judy44chen.github.io/TTSSpeechBERT/.

eess.AS↗

arXiv2017

A homotopy method for computing the largest eigenvalue of an irreducible nonnegative tensor

In this paper we propose a homotopy method to compute the largest eigenvalue and a corresponding eigenvector of a nonnegative tensor. We prove that it converges to the desired eigenpair when the tensor is irreducible. We also implement the method using an prediction-correction approach for path following. Some numerical results are provided to illustrate the efficiency of the method.

math.NA↗

arXiv2016

Understanding the fundamental connection between electronic correlation and decoherence

We introduce a theory that exposes the fundamental and previously overlooked connection between the correlation among electrons and the degree of quantum coherence of electronic states in matter. For arbitrary states, the effects only decouple when the electronic dynamics induced by the nuclear bath is pure-dephasing in nature such that $[H^{S},H^{SB}]=0$, where $H^{S}$ is the electronic Hamiltonian and $H^{SB}$ is the electron-nuclear coupling. We quantitatively illustrate this connection via exact simulations of a Hubbard-Holstein molecule using the Hierarchical Equations of Motion that show that increasing the degree of electronic interactions can enhance or suppress the rate of electronic coherence loss.

quant-ph↗

arXiv2016

Crowdsourcing On-street Parking Space Detection

As the number of vehicles continues to grow, parking spaces are at a premium in city streets. Additionally, due to the lack of knowledge about street parking spaces, heuristic circling the blocks not only costs drivers' time and fuel, but also increases city congestion. In the wake of recent trend to build convenient, green and energy-efficient smart cities, we rethink common techniques adopted by high-profile smart parking systems, and present a user-engaged (crowdsourcing) and sonar-based prototype to identify urban on-street parking spaces. The prototype includes an ultrasonic sensor, a GPS receiver and associated Arduino micro-controllers. It is mounted on the passenger side of a car to measure the distance from the vehicle to the nearest roadside obstacle. Multiple road tests are conducted around Wheatley, Oxford to gather results and emulate the crowdsourcing approach. By extracting parked vehicles' features from the collected trace, a supervised learning algorithm is developed to estimate roadside parking occupancy and spot illegal parking vehicles. A quantity estimation model is derived to calculate the required number of sensing units to cover urban streets. The estimation is quantitatively compared to a fixed sensing solution. The results show that the crowdsourcing way would need substantially fewer sensors compared to the fixed sensing system.

cs.HC↗

arXiv2016

Computing tensor eigenvalues via homotopy methods

We introduce the concept of mode-k generalized eigenvalues and eigenvectors of a tensor and prove some properties of such eigenpairs. In particular, we derive an upper bound for the number of equivalence classes of generalized tensor eigenpairs using mixed volume. Based on this bound and the structures of tensor eigenvalue problems, we propose two homotopy continuation type algorithms to solve tensor eigenproblems. With proper implementation, these methods can find all equivalence classes of isolated generalized eigenpairs and some generalized eigenpairs contained in the positive dimensional components (if there are any). We also introduce an algorithm that combines a heuristic approach and a Newton homotopy method to extract real generalized eigenpairs from the found complex generalized eigenpairs. A MATLAB software package TenEig has been developed to implement these methods. Numerical results are presented to illustrate the effectiveness and efficiency of TenEig for computing complex or real generalized eigenpairs.

math.NA↗

arXiv2011

A sol-gel method for growing superconducting MgB2 films

In this paper we report a new sol-gel method for the fabrication of MgB2 films. Polycrystalline MgB2 films were prepared by spin-coating a precursor solution of Mg(BH_4)_2 diethyl ether on (001)Al2O3 substrates followed with annealing in Mg vapor. In comparison with the MgB2 films grown by other techniques, our films show medium qualities including a superconducting transition temperature of Tc ~ 37 K, a critical current density of Jc(5 K, 0 T) ~ 5 {\times} 10^6 A cm^{-2}, and a critical field of H_{c2}(0) ~ 19 T. Such a sol-gel technique shows potential in the commercial fabrication of practically used MgB2 films as well as MgB2 wires and tapes.

cond-mat.supr-con↗

arXiv2010

Theory of proton coupled electron transfer reactions: Assessing the Born-Oppenheimer approximation for the proton motion using an analytically solvable model

By employing an analytically solvable model including the Duschinsky rotation effect, we investigated the applicability of the commonly used Born-Oppenheimer (BO) approximation for separating the proton and proton donor-acceptor motions in theories of proton coupled electron transfer (PCET) reactions. Comparison with theories based on the BO approximation shows that, the BO approximation for the proton coordinate is generally valid while some further approximations may become inaccurate in certain range of parameters. We have also investigated the effect of vibrationally coherent tunneling in the case of small reorganization energy, and shown that it plays an important role on the rate constant and kinetic isotope effect.

physics.chem-ph↗