arXiv subjects

Lei Xie

Publications and source records attributed to Lei Xie.

At least 397 records · Page 22Linked to original sources

arXiv2022

Reinforcement Learning for Personalized Drug Discovery and Design for Complex Diseases: A Systems Pharmacology Perspective

Many multi-genic systemic diseases such as neurological disorders, inflammatory diseases, and the majority of cancers do not have effective treatments yet. Reinforcement learning powered systems pharmacology is a potentially effective approach to design personalized therapies for untreatable complex diseases. In this survey, state-of-the-art reinforcement learning methods and their latest applications to drug design are reviewed. The challenges on harnessing reinforcement learning for systems pharmacology and personalized medicine are discussed. Potential solutions to overcome the challenges are proposed. In spite of successful application of advanced reinforcement learning techniques to target-based drug discovery, new reinforcement learning strategies are needed to address systems pharmacology-oriented personalized de novo drug design.

q-bio.BM↗

arXiv2022

One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation

One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion approach for style transfer based on speaker adaptation. First, a speaker normalization module is adopted to remove speaker-related information in bottleneck features extracted by ASR. Second, we adopt weight regularization in the adaptation process to prevent over-fitting caused by using only one utterance from target speaker as training data. Finally, to comprehensively decouple the speech factors, i.e., content, speaker, style, and transfer source style to the target, a prosody module is used to extract prosody representation. Experiments show that our approach is superior to the state-of-the-art one-shot VC systems in terms of style and speaker similarity; additionally, our approach also maintains good speech quality.

eess.AS↗

arXiv2022

Multi-Task Deep Residual Echo Suppression with Echo-aware Loss

This paper introduces the NWPU Team's entry to the ICASSP 2022 AEC Challenge. We take a hybrid approach that cascades a linear AEC with a neural post-filter. The former is used to deal with the linear echo components while the latter suppresses the residual non-linear echo components. We use gated convolutional F-T-LSTM neural network (GFTNN) as the backbone and shape the post-filter by a multi-task learning (MTL) framework, where a voice activity detection (VAD) module is adopted as an auxiliary task along with echo suppression, with the aim to avoid over suppression that may cause speech distortion. Moreover, we adopt an echo-aware loss function, where the mean square error (MSE) loss can be optimized particularly for every time-frequency bin (TF-bin) according to the signal-to-echo ratio (SER), leading to further suppression on the echo. Extensive ablation study shows that the time delay estimation (TDE) module in neural post-filter leads to better perceptual quality, and an adaptive filter with better convergence will bring consistent performance gain for the post-filter. Besides, we find that using the linear echo as the input of our neural post-filter is a better choice than using the reference signal directly. In the ICASSP 2022 AEC-Challenge, our approach has ranked the 1st place on word accuracy (WAcc) (0.817) and the 3rd place on both mean opinion score (MOS) (4.502) and the final score (0.864).

cs.SD↗

arXiv2022

Conversational Speech Recognition By Learning Conversation-level Characteristics

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of conversation, such as role preference and topical coherence. This paper proposes a conversational ASR model which explicitly learns conversation-level characteristics under the prevalent end-to-end neural framework. The highlights of the proposed model are twofold. First, a latent variational module (LVM) is attached to a conformer-based encoder-decoder ASR backbone to learn role preference and topical coherence. Second, a topic model is specifically adopted to bias the outputs of the decoder to words in the predicted topics. Experiments on two Mandarin conversational ASR tasks show that the proposed model achieves a maximum 12% relative character error rate (CER) reduction.

cs.SD↗

arXiv2022

Suppressing ZZ Crosstalk of Quantum Computers through Pulse and Scheduling Co-Optimization

Noise is a significant obstacle to quantum computing, and $ZZ$ crosstalk is one of the most destructive types of noise affecting superconducting qubits. Previous approaches to suppressing $ZZ$ crosstalk have mainly relied on specific chip design that can complicate chip fabrication and aggravate decoherence. To some extent, special chip design can be avoided by relying on pulse optimization to suppress $ZZ$ crosstalk. However, existing approaches are non-scalable, as their required time and memory grow exponentially with the number of qubits involved. To address the above problems, we propose a scalable approach by co-optimizing pulses and scheduling. We optimize pulses to offer an ability to suppress $ZZ$ crosstalk surrounding a gate, and then design scheduling strategies to exploit this ability and achieve suppression across the whole circuit. A main advantage of such co-optimization is that it does not require special hardware support. Besides, we implement our approach as a general framework that is compatible with different pulse optimization methods. We have conducted extensive evaluations by simulation and on a real quantum computer. Simulation results show that our proposal can improve the fidelity of quantum computing on $4{\sim}12$ qubits by up to $81\times$ ($11\times$ on average). Ramsey experiments on a real quantum computer also demonstrate that our method can eliminate the effect of $ZZ$ crosstalk to a great extent.

quant-ph↗

arXiv2022

Regularized Covariance Estimation for Polarization Radar Detection in Compound Gaussian Sea Clutter

This paper investigates regularized estimation of Kronecker-structured covariance matrices (CM) for polarization radar in sea clutter scenarios where the data are assumed to follow the complex, elliptically symmetric (CES) distributions with a Kronecker-structured CM. To obtain a well-conditioned estimate of the CM, we add penalty terms of Kullback-Leibler divergence to the negative log-likelihood function of the associated complex angular Gaussian (CAG) distribution. This is shown to be equivalent to regularizing Tyler's fixed-point equations by shrinkage. A sufficient condition that the solution exists is discussed. An iterative algorithm is applied to solve the resulting fixed-point iterations and its convergence is proved. In order to solve the critical problem of tuning the shrinkage factors, we then introduce two methods by exploiting oracle approximating shrinkage (OAS) and cross-validation (CV). The proposed estimator, referred to as the robust shrinkage Kronecker estimator (RSKE), is shown to achieve better performance compared with several existing methods when the training samples are limited. Simulations are conducted for validating the RSKE and demonstrating its high performance by using the IPIX 1998 real sea data.

eess.SP↗

arXiv2022

Noise-robust voice conversion with domain adversarial training

Voice conversion has made great progress in the past few years under the studio-quality test scenario in terms of speech quality and speaker similarity. However, in real applications, test speech from source speaker or target speaker can be corrupted by various environment noises, which seriously degrade the speech quality and speaker similarity. In this paper, we propose a novel encoder-decoder based noise-robust voice conversion framework, which consists of a speaker encoder, a content encoder, a decoder, and two domain adversarial neural networks. Specifically, we integrate disentangling speaker and content representation technique with domain adversarial training technique. Domain adversarial training makes speaker representations and content representations extracted by speaker encoder and content encoder from clean speech and noisy speech in the same space, respectively. In this way, the learned speaker and content representations are noise-invariant. Therefore, the two noise-invariant representations can be taken as input by the decoder to predict the clean converted spectrum. The experimental results demonstrate that our proposed method can synthesize clean converted speech under noisy test scenarios, where the source speech and target speech can be corrupted by seen or unseen noise types during the training process. Additionally, both speech quality and speaker similarity are improved.

cs.SD↗

arXiv2022

Disentangling Style and Speaker Attributes for TTS Style Transfer

End-to-end neural TTS has shown improved performance in speech style transfer. However, the improvement is still limited by the available training data in both target styles and speakers. Additionally, degenerated performance is observed when the trained TTS tries to transfer the speech to a target style from a new speaker with an unknown, arbitrary style. In this paper, we propose a new approach to seen and unseen style transfer training on disjoint, multi-style datasets, i.e., datasets of different styles are recorded, one individual style by one speaker in multiple utterances. An inverse autoregressive flow (IAF) technique is first introduced to improve the variational inference for learning an expressive style representation. A speaker encoder network is then developed for learning a discriminative speaker embedding, which is jointly trained with the rest neural TTS modules. The proposed approach of seen and unseen style transfer is effectively trained with six specifically-designed objectives: reconstruction loss, adversarial loss, style distortion loss, cycle consistency loss, style classification loss, and speaker classification loss. Experiments demonstrate, both objectively and subjectively, the effectiveness of the proposed approach for seen and unseen style transfer tasks. The performance of our approach is superior to and more robust than those of four other reference systems of prior art.

cs.SD↗

arXiv2022

Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

This paper introduces Opencpop, a publicly available high-quality Mandarin singing corpus designed for singing voice synthesis (SVS). The corpus consists of 100 popular Mandarin songs performed by a female professional singer. Audio files are recorded with studio quality at a sampling rate of 44,100 Hz and the corresponding lyrics and musical scores are provided. All singing recordings have been phonetically annotated with phoneme boundaries and syllable (note) boundaries. To demonstrate the reliability of the released data and to provide a baseline for future research, we built baseline deep neural network-based SVS models and evaluated them with both objective metrics and subjective mean opinion score (MOS) measure. Experimental results show that the best SVS model trained on our database achieves 3.70 MOS, indicating the reliability of the provided corpus. Opencpop is released to the open-source community WeNet, and the corpus, as well as synthesized demos, can be found on the project homepage.

cs.SD↗

arXiv2022

MsEmoTTS: Multi-scale emotion transfer, prediction, and control for emotional speech synthesis

Expressive synthetic speech is essential for many human-computer interaction and audio broadcast scenarios, and thus synthesizing expressive speech has attracted much attention in recent years. Previous methods performed the expressive speech synthesis either with explicit labels or with a fixed-length style embedding extracted from reference audio, both of which can only learn an average style and thus ignores the multi-scale nature of speech prosody. In this paper, we propose MsEmoTTS, a multi-scale emotional speech synthesis framework, to model the emotion from different levels. Specifically, the proposed method is a typical attention-based sequence-to-sequence model and with proposed three modules, including global-level emotion presenting module (GM), utterance-level emotion presenting module (UM), and local-level emotion presenting module (LM), to model the global emotion category, utterance-level emotion variation, and syllable-level emotion strength, respectively. In addition to modeling the emotion from different levels, the proposed method also allows us to synthesize emotional speech in different ways, i.e., transferring the emotion from reference audio, predicting the emotion from input text, and controlling the emotion strength manually. Extensive experiments conducted on a Chinese emotional speech corpus demonstrate that the proposed method outperforms the compared reference audio-based and text-based emotional speech synthesis methods on the emotion transfer speech synthesis and text-based emotion prediction speech synthesis respectively. Besides, the experiments also show that the proposed method can control the emotion expressions flexibly. Detailed analysis shows the effectiveness of each module and the good design of the proposed method.

cs.SD↗

arXiv2022

IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion

Prosody modeling is important, but still challenging in expressive voice conversion. As prosody is difficult to model, and other factors, e.g., speaker, environment and content, which are entangled with prosody in speech, should be removed in prosody modeling. In this paper, we present IQDubbing to solve this problem for expressive voice conversion. To model prosody, we leverage the recent advances in discrete self-supervised speech representation (DSSR). Specifically, prosody vector is first extracted from pre-trained VQ-Wav2Vec model, where rich prosody information is embedded while most speaker and environment information are removed effectively by quantization. To further filter out the redundant information except prosody, such as content and partial speaker information, we propose two kinds of prosody filters to sample prosody from the prosody vector. Experiments show that IQDubbing is superior to baseline and comparison systems in terms of speech quality while maintaining prosody consistency and speaker similarity.

eess.AS↗

arXiv2021

Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition

In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. Our model adopts the hybrid CTC/attention architecture, in which the conformer layers in the encoder are modified. We propose a dynamic chunk-based attention strategy to allow arbitrary right context length. At inference time, the CTC decoder generates n-best hypotheses in a streaming way. The inference latency could be easily controlled by only changing the chunk size. The CTC hypotheses are then rescored by the attention decoder to get the final result. This efficient rescoring process causes very little sentence-level latency. Our experiments on the open 170-hour AISHELL-1 dataset show that, the proposed method can unify the streaming and non-streaming model simply and efficiently. On the AISHELL-1 test set, our unified model achieves 5.60% relative character error rate (CER) reduction in non-streaming ASR compared to a standard non-streaming transformer. The same model achieves 5.42% CER with 640ms latency in a streaming ASR system.

cs.SD↗

arXiv2021

WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit

In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. The main motivation of WeNet is to close the gap between the research and the production of E2E speechrecognition models. WeNet provides an efficient way to ship ASR applications in several real-world scenarios, which is the main difference and advantage to other open source E2E speech recognition toolkits. In our toolkit, a new two-pass method is implemented. Our method propose a dynamic chunk-based attention strategy of the the transformer layers to allow arbitrary right context length modifies in hybrid CTC/attention architecture. The inference latency could be easily controlled by only changing the chunk size. The CTC hypotheses are then rescored by the attention decoder to get the final result. Our experiments on the AISHELL-1 dataset using WeNet show that, our model achieves 5.03\% relative character error rate (CER) reduction in non-streaming ASR compared to a standard non-streaming transformer. After model quantification, our model perform reasonable RTF and latency.

cs.SD↗

arXiv2021

Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios

In the existing cross-speaker style transfer task, a source speaker with multi-style recordings is necessary to provide the style for a target speaker. However, it is hard for one speaker to express all expected styles. In this paper, a more general task, which is to produce expressive speech by combining any styles and timbres from a multi-speaker corpus in which each speaker has a unique style, is proposed. To realize this task, a novel method is proposed. This method is a Tacotron2-based framework but with a fine-grained text-based prosody predicting module and a speaker identity controller. Experiments demonstrate that the proposed method can successfully express a style of one speaker with the timber of another speaker bypassing the dependency on a single speaker's multi-style corpus. Moreover, the explicit prosody features used in the prosody predicting module can increase the diversity of synthetic speech by adjusting the value of prosody features.

eess.AS↗

arXiv2021

A Computational Efficient Maximum Likelihood Direct Position Determination Approach for Multiple Emitters Using Angle and Doppler Measurements

Emitter localization is widely applied in the military and civilian _elds. In this paper, we tackle the problem of position estimation for multiple stationary emitters using Doppler frequency shifts and angles by moving receivers. The computational load for the exhaustive maximum likelihood (ML) direct position determination (DPD) search is insu_erable. Based on the Pincus' theorem and importance sampling (IS) concept, we propose a novel non-iterative ML DPD method. The proposed method transforms the original multidimensional grid search into random variables generation with multiple low-dimensional pseudo-probability density functions (PDF), and the circular mean is used for superior position estimation performance. The computational complexity of the proposed method is modest, and the o_-grid problem that most existing DPD techniques face is signi_cantly alleviated. Moreover, it can be implemented in parallel separately. Simulation results demonstrate that the proposed ML DPD estimator can achieve better estimation accuracy than state-of-the-art DPD techniques. With a reasonable parameter choice, the estimation performance of the proposed technique is very close to the Cram_er-Rao lower bound (CRLB), even in the adverse conditions of low signal-to-noise ratios (SNR) levels.

eess.SP↗

arXiv2021

Exploration of Dark Chemical Genomics Space via Portal Learning: Applied to Targeting the Undruggable Genome and COVID-19 Anti-Infective Polypharmacology

Advances in biomedicine are largely fueled by exploring uncharted territories of human biology. Machine learning can both enable and accelerate discovery, but faces a fundamental hurdle when applied to unseen data with distributions that differ from previously observed ones -- a common dilemma in scientific inquiry. We have developed a new deep learning framework, called {\textit{Portal Learning}}, to explore dark chemical and biological space. Three key, novel components of our approach include: (i) end-to-end, step-wise transfer learning, in recognition of biology's sequence-structure-function paradigm, (ii) out-of-cluster meta-learning, and (iii) stress model selection. Portal Learning provides a practical solution to the out-of-distribution (OOD) problem in statistical machine learning. Here, we have implemented Portal Learning to predict chemical-protein interactions on a genome-wide scale. Systematic studies demonstrate that Portal Learning can effectively assign ligands to unexplored gene families (unknown functions), versus existing state-of-the-art methods, thereby allowing us to target previously "undruggable" proteins and design novel polypharmacological agents for disrupting interactions between SARS-CoV-2 and human proteins. Portal Learning is general-purpose and can be further applied to other areas of scientific inquiry.

q-bio.QM↗

arXiv2021

Beijing ZKJ-NPU Speaker Verification System for VoxCeleb Speaker Recognition Challenge 2021

In this report, we describe the Beijing ZKJ-NPU team submission to the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). We participated in the fully supervised speaker verification track 1 and track 2. In the challenge, we explored various kinds of advanced neural network structures with different pooling layers and objective loss functions. In addition, we introduced the ResNet-DTCF, CoAtNet and PyConv networks to advance the performance of CNN-based speaker embedding model. Moreover, we applied embedding normalization and score normalization at the evaluation stage. By fusing 11 and 14 systems, our final best performances (minDCF/EER) on the evaluation trails are 0.1205/2.8160% and 0.1175/2.8400% respectively for track 1 and 2. With our submission, we came to the second place in the challenge for both tracks.

cs.SD↗

arXiv2021

S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancement

In speech enhancement, complex neural network has shown promising performance due to their effectiveness in processing complex-valued spectrum. Most of the recent speech enhancement approaches mainly focus on wide-band signal with a sampling rate of 16K Hz. However, research on super wide band (e.g., 32K Hz) or even full-band (48K) denoising is still lacked due to the difficulty of modeling more frequency bands and particularly high frequency components. In this paper, we extend our previous deep complex convolution recurrent neural network (DCCRN) substantially to a super wide band version -- S-DCCRN, to perform speech denoising on speech of 32K Hz sampling rate. We first employ a cascaded sub-band and full-band processing module, which consists of two small-footprint DCCRNs -- one operates on sub-band signal and one operates on full-band signal, aiming at benefiting from both local and global frequency information. Moreover, instead of simply adopting the STFT feature as input, we use a complex feature encoder trained in an end-to-end manner to refine the information of different frequency bands. We also use a complex feature decoder to revert the feature to time-frequency domain. Finally, a learnable spectrum compression method is adopted to adjust the energy of different frequency bands, which is beneficial for neural network learning. The proposed model, S-DCCRN, has surpassed PercepNet as well as several competitive models and achieves state-of-the-art performance in terms of speech quality and intelligibility. Ablation studies also demonstrate the effectiveness of different contributions.

eess.AS↗