arXiv subjects

Xiaorui Wang

Publications and source records attributed to Xiaorui Wang.

51 records · Page 3Linked to original sources

arXiv2022

Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis

Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesised speech of a target speaker's timbre. Most previous approaches rely on data with style labels, but manually-annotated labels are expensive and not always reliable. In response to this problem, we propose Style-Label-Free, a cross-speaker style transfer method, which can realize the style transfer from source speaker to target speaker without style labels. Firstly, a reference encoder structure based on quantized variational autoencoder (Q-VAE) and style bottleneck is designed to extract discrete style representations. Secondly, a speaker-wise batch normalization layer is proposed to reduce the source speaker leakage. In order to improve the style extraction ability of the reference encoder, a style invariant and contrastive data augmentation method is proposed. Experimental results show that the method outperforms the baseline. We provide a website with audio samples.

cs.SD↗

arXiv2022

Back-Translation-Style Data Augmentation for Mandarin Chinese Polyphone Disambiguation

Conversion of Chinese Grapheme-to-Phoneme (G2P) plays an important role in Mandarin Chinese Text-To-Speech (TTS) systems, where one of the biggest challenges is the task of polyphone disambiguation. Most of the previous polyphone disambiguation models are trained on manually annotated datasets, and publicly available datasets for polyphone disambiguation are scarce. In this paper we propose a simple back-translation-style data augmentation method for mandarin Chinese polyphone disambiguation, utilizing a large amount of unlabeled text data. Inspired by the back-translation technique proposed in the field of machine translation, we build a Grapheme-to-Phoneme (G2P) model to predict the pronunciation of polyphonic character, and a Phoneme-to-Grapheme (P2G) model to predict pronunciation into text. Meanwhile, a window-based matching strategy and a multi-model scoring strategy are proposed to judge the correctness of the pseudo-label. We design a data balance strategy to improve the accuracy of some typical polyphonic characters in the training set with imbalanced distribution or data scarcity. The experimental result shows the effectiveness of the proposed back-translation-style data augmentation method.

cs.SD↗

arXiv2022

SA4U: Practical Static Analysis for Unit Type Error Detection

Unit type errors, where values with physical unit types (e.g., meters, hours) are used incorrectly in a computation, are common in today's unmanned aerial system (UAS) firmware. Recent studies show that unit type errors represent over 10% of bugs in UAS firmware. Moreover, the consequences of unit type errors are severe. Over 30% of unit type errors cause UAS crashes. This paper proposes SA4U: a practical system for detecting unit type errors in real-world UAS firmware. SA4U requires no modifications to firmware or developer annotations. It deduces the unit types of program variables by analyzing simulation traces and protocol definitions. SA4U uses the deduced unit types to identify when unit type errors occur. SA4U is effective: it identified 14 previously undetected bugs in two popular open-source firmware (ArduPilot & PX4.)

cs.SE↗

arXiv2022

Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition

While transformers and their variant conformers show promising performance in speech recognition, the parameterized property leads to much memory cost during training and inference. Some works use cross-layer weight-sharing to reduce the parameters of the model. However, the inevitable loss of capacity harms the model performance. To address this issue, this paper proposes a parameter-efficient conformer via sharing sparsely-gated experts. Specifically, we use sparsely-gated mixture-of-experts (MoE) to extend the capacity of a conformer block without increasing computation. Then, the parameters of the grouped conformer blocks are shared so that the number of parameters is reduced. Next, to ensure the shared blocks with the flexibility of adapting representations at different levels, we design the MoE routers and normalization individually. Moreover, we use knowledge distillation to further improve the performance. Experimental results show that the proposed model achieves competitive performance with 1/3 of the parameters of the encoder, compared with the full-parameter model.

eess.AS↗

arXiv2021

MELONS: generating melody with long-term structure using transformers and structure graph

The creation of long melody sequences requires effective expression of coherent musical structure. However, there is no clear representation of musical structure. Recent works on music generation have suggested various approaches to deal with the structural information of music, but generating a full-song melody with clear long-term structure remains a challenge. In this paper, we propose MELONS, a melody generation framework based on a graph representation of music structure which consists of eight types of bar-level relations. MELONS adopts a multi-step generation method with transformer-based networks by factoring melody generation into two sub-problems: structure generation and structure conditional melody generation. Experimental results show that MELONS can produce structured melodies with high quality and rich contents.

cs.SD↗

arXiv2021

SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification

Recently, x-vector has been a successful and popular approach for speaker verification, which employs a time delay neural network (TDNN) and statistics pooling to extract speaker characterizing embedding from variable-length utterances. Improvement upon the x-vector has been an active research area, and enormous neural networks have been elaborately designed based on the x-vector, eg, extended TDNN (E-TDNN), factorized TDNN (F-TDNN), and densely connected TDNN (D-TDNN). In this work, we try to identify the optimal architectures from a TDNN based search space employing neural architecture search (NAS), named SpeechNAS. Leveraging the recent advances in the speaker recognition, such as high-order statistics pooling, multi-branch mechanism, D-TDNN and angular additive margin softmax (AAM) loss with a minimum hyper-spherical energy (MHE), SpeechNAS automatically discovers five network architectures, from SpeechNAS-1 to SpeechNAS-5, of various numbers of parameters and GFLOPs on the large-scale text-independent speaker recognition dataset VoxCeleb1. Our derived best neural network achieves an equal error rate (EER) of 1.02% on the standard test set of VoxCeleb1, which surpasses previous TDNN based state-of-the-art approaches by a large margin. Code and trained weights are in https://github.com/wentaozhu/speechnas.git

cs.SD↗

arXiv2021

Dynamic Multi-scale Convolution for Dialect Identification

Time Delay Neural Networks (TDNN)-based methods are widely used in dialect identification. However, in previous work with TDNN application, subtle variant is being neglected in different feature scales. To address this issue, we propose a new architecture, named dynamic multi-scale convolution, which consists of dynamic kernel convolution, local multi-scale learning, and global multi-scale pooling. Dynamic kernel convolution captures features between short-term and long-term context adaptively. Local multi-scale learning, which represents multi-scale features at a granular level, is able to increase the range of receptive fields for convolution operation. Besides, global multi-scale pooling is applied to aggregate features from different bottleneck layers in order to collect information from multiple aspects. The proposed architecture significantly outperforms state-of-the-art system on the AP20-OLR-dialect-task of oriental language recognition (OLR) challenge 2020, with the best average cost performance (Cavg) of 0.067 and the best equal error rate (EER) of 6.52%. Compared with the known best results, our method achieves 9% of Cavg and 45% of EER relative improvement, respectively. Furthermore, the parameters of proposed model are 91% fewer than the best known model.

cs.CL↗

arXiv2021

Multi-Task Audio Source Separation

The audio source separation tasks, such as speech enhancement, speech separation, and music source separation, have achieved impressive performance in recent studies. The powerful modeling capabilities of deep neural networks give us hope for more challenging tasks. This paper launches a new multi-task audio source separation (MTASS) challenge to separate the speech, music, and noise signals from the monaural mixture. First, we introduce the details of this task and generate a dataset of mixtures containing speech, music, and background noises. Then, we propose an MTASS model in the complex domain to fully utilize the differences in spectral characteristics of the three audio signals. In detail, the proposed model follows a two-stage pipeline, which separates the three types of audio signals and then performs signal compensation separately. After comparing different training targets, the complex ratio mask is selected as a more suitable target for the MTASS. The experimental results also indicate that the residual signal compensation module helps to recover the signals further. The proposed model shows significant advantages in separation performance over several well-known separation models.

eess.AS↗

arXiv2021

Gaussian Dynamic Convolution for Efficient Single-Image Segmentation

Interactive single-image segmentation is ubiquitous in the scientific and commercial imaging software. In this work, we focus on the single-image segmentation problem only with some seeds such as scribbles. Inspired by the dynamic receptive field in the human being's visual system, we propose the Gaussian dynamic convolution (GDC) to fast and efficiently aggregate the contextual information for neural networks. The core idea is randomly selecting the spatial sampling area according to the Gaussian distribution offsets. Our GDC can be easily used as a module to build lightweight or complex segmentation networks. We adopt the proposed GDC to address the typical single-image segmentation tasks. Furthermore, we also build a Gaussian dynamic pyramid Pooling to show its potential and generality in common semantic segmentation. Experiments demonstrate that the GDC outperforms other existing convolutions on three benchmark segmentation datasets including Pascal-Context, Pascal-VOC 2012, and Cityscapes. Additional experiments are also conducted to illustrate that the GDC can produce richer and more vivid features compared with other convolutions. In general, our GDC is conducive to the convolutional neural networks to form an overall impression of the image.

cs.CV↗

arXiv2020

Thermal transport enhancement of hybrid nanocomposites; impact of confined water inside nanoporous silicon

The thermal transport properties of porous silicon and nano-hybrid "porous silicon/water" systems are presented here. The thermal conductivity was evaluated with equilibrium molecular dynamics technique for porous systems made of spherical voids or water-filled cavities. We revealed large thermal conductivity enhancement in the nano-hybrid systems as compared to their dry porous counterparts, which cannot be captured by effective media theory. This rise of thermal conductivity is related to the increases of the specific surface of the liquid/solid interface. We demonstrated that significant difference for more than two folds of thermal conductivity of pristine porous silicon and "porous silicon liquid/composite" is due to the liquid density fluctuation close to "solid/liquid interface" (layering effect). This effect is getting more important for the high specific surface of the interfacial area. Specifically, the enhancement of the effective thermal conductivity is 50 % for specific surface area of 0.3 (1/nm), and it increases further upon the increase of the surface to volume ratio. Our study provides valuable insights into the thermal properties of hybrid liquid/solid nanocomposites and about the importance of confined liquids within nanoporous materials.

cond-mat.mes-hall↗

arXiv2019

a novel cross-lingual voice cloning approach with a few text-free samples

In this paper, we present a cross-lingual voice cloning approach. BN features obtained by SI-ASR model are used as a bridge across speakers and language boundaries. The relationships between text and BN features are modeled by the latent prosody model. The acoustic model learns the translation from BN features to acoustic features. The acoustic model is fine-tuned with a few samples of the target speaker to realize voice cloning. This system can generate speech of arbitrary utterance of target language in cross-lingual speakers' voice. We verify that with small amount of audio data, our proposed approach can well handle cross-lingual tasks. And in intra-lingual tasks, our proposed approach also performs better than baseline approach in naturalness and similarity.

eess.AS↗

arXiv2018

Improving Gated Recurrent Unit Based Acoustic Modeling with Batch Normalization and Enlarged Context

The use of future contextual information is typically shown to be helpful for acoustic modeling. Recently, we proposed a RNN model called minimal gated recurrent unit with input projection (mGRUIP), in which a context module namely temporal convolution, is specifically designed to model the future context. This model, mGRUIP with context module (mGRUIP-Ctx), has been shown to be able of utilizing the future context effectively, meanwhile with quite low model latency and computation cost. In this paper, we continue to improve mGRUIP-Ctx with two revisions: applying BN methods and enlarging model context. Experimental results on two Mandarin ASR tasks (8400 hours and 60K hours) show that, the revised mGRUIP-Ctx outperform LSTM with a large margin (11% to 38%). It even performs slightly better than a superior BLSTM on the 8400h task, with 33M less parameters and just 290ms model latency.

cs.CL↗

arXiv2018

Gated Recurrent Unit Based Acoustic Modeling with Future Context

The use of future contextual information is typically shown to be helpful for acoustic modeling. However, for the recurrent neural network (RNN), it's not so easy to model the future temporal context effectively, meanwhile keep lower model latency. In this paper, we attempt to design a RNN acoustic model that being capable of utilizing the future context effectively and directly, with the model latency and computation cost as low as possible. The proposed model is based on the minimal gated recurrent unit (mGRU) with an input projection layer inserted in it. Two context modules, temporal encoding and temporal convolution, are specifically designed for this architecture to model the future context. Experimental results on the Switchboard task and an internal Mandarin ASR task show that, the proposed model performs much better than long short-term memory (LSTM) and mGRU models, whereas enables online decoding with a maximum latency of 170 ms. This model even outperforms a very strong baseline, TDNN-LSTM, with smaller model latency and almost half less parameters.

cs.CL↗

arXiv2011

Evidence of an Internally Generated Optical-Dipole Potential in Matter-Wave Superradiance

We present the first experimental evidence supporting the postulation that an optical-dipole potential in a condensate undergoing superradiant scattering modifies the structure factor of the system and significantly impacts the scattering. Several consequences of this new detuning-dependent mechanism are discussed and verified experimentally. Our experiments indicate that whenever the generation and propagation growth of a new field are significant, the dynamic response of the condensate can have a profound impact on the scattering process.

quant-ph↗

arXiv2010

Observation of a red-blue detuning asymmetry in matter-wave superradiance

We report the first experimental observations of strong suppression of matter-wave superradiance using blue-detuned pump light and demonstrate a pump-laser detuning asymmetry in the collective atomic recoil motion. In contrast to all previous theoretical frameworks, which predict that the process should be symmetric with respect to the sign of the pump-laser detuning, we find that for condensates the symmetry is broken. With high condensate densities and red-detuned light, the familiar distinctive multi-order, matter-wave scattering pattern is clearly visible, whereas with blue-detuned light superradiance is strongly suppressed. In the limit of a dilute atomic gas, however, symmetry is restored.

cond-mat.quant-gas↗