arXiv subjects

Lei Xie

Publications and source records attributed to Lei Xie.

At least 343 records · Page 19Linked to original sources

arXiv2023

Multi-Speaker Expressive Speech Synthesis via Multiple Factors Decoupling

This paper aims to synthesize the target speaker's speech with desired speaking style and emotion by transferring the style and emotion from reference speech recorded by other speakers. We address this challenging problem with a two-stage framework composed of a text-to-style-and-emotion (Text2SE) module and a style-and-emotion-to-wave (SE2Wave) module, bridging by neural bottleneck (BN) features. To further solve the multi-factor (speaker timbre, speaking style and emotion) decoupling problem, we adopt the multi-label binary vector (MBV) and mutual information (MI) minimization to respectively discretize the extracted embeddings and disentangle these highly entangled factors in both Text2SE and SE2Wave modules. Moreover, we introduce a semi-supervised training strategy to leverage data from multiple speakers, including emotion-labeled data, style-labeled data, and unlabeled data. To better transfer the fine-grained expression from references to the target speaker in non-parallel transfer, we introduce a reference-candidate pool and propose an attention-based reference selection approach. Extensive experiments demonstrate the good design of our model.

eess.AS↗

arXiv2023

VE-KWS: Visual Modality Enhanced End-to-End Keyword Spotting

The performance of the keyword spotting (KWS) system based on audio modality, commonly measured in false alarms and false rejects, degrades significantly under the far field and noisy conditions. Therefore, audio-visual keyword spotting, which leverages complementary relationships over multiple modalities, has recently gained much attention. However, current studies mainly focus on combining the exclusively learned representations of different modalities, instead of exploring the modal relationships during each respective modeling. In this paper, we propose a novel visual modality enhanced end-to-end KWS framework (VE-KWS), which fuses audio and visual modalities from two aspects. The first one is utilizing the speaker location information obtained from the lip region in videos to assist the training of multi-channel audio beamformer. By involving the beamformer as an audio enhancement module, the acoustic distortions, caused by the far field or noisy environments, could be significantly suppressed. The other one is conducting cross-attention between different modalities to capture the inter-modal relationships and help the representation learning of each modality. Experiments on the MSIP challenge corpus show that our proposed model achieves 2.79% false rejection rate and 2.95% false alarm rate on the Eval set, resulting in a new SOTA performance compared with the top-ranking systems in the ICASSP2022 MISP challenge.

cs.SD↗

arXiv2023

Two-stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge

In ICASSP 2023 speech signal improvement challenge, we developed a dual-stage neural model which improves speech signal quality induced by different distortions in a stage-wise divide-and-conquer fashion. Specifically, in the first stage, the speech improvement network focuses on recovering the missing components of the spectrum, while in the second stage, our model aims to further suppress noise, reverberation, and artifacts introduced by the first-stage model. Achieving 0.446 in the final score and 0.517 in the P.835 score, our system ranks 4th in the non-real-time track.

eess.AS↗

arXiv2023

Two-step Band-split Neural Network Approach for Full-band Residual Echo Suppression

This paper describes a Two-step Band-split Neural Network (TBNN) approach for full-band acoustic echo cancellation. Specifically, after linear filtering, we split the full-band signal into wide-band (16KHz) and high-band (16-48KHz) for residual echo removal with lower modeling difficulty. The wide-band signal is processed by an updated gated convolutional recurrent network (GCRN) with U$^2$ encoder while the high-band signal is processed by a high-band post-filter net with lower complexity. Our approach submitted to ICASSP 2023 AEC Challenge has achieved an overall mean opinion score (MOS) of 4.344 and a word accuracy (WAcc) ratio of 0.795, leading to the 2$^{nd}$ (tied) in the ranking of the non-personalized track.

eess.AS↗

arXiv2023

Entangling spins using cubic nonlinear dynamics

Entangled states with a large number of $N$ atomic spins are a key ingredient for quantum information processing and quantum metrology. Nowadays, the preparation of such states has mainly relied on the quadratic nonlinear dynamics. Here, we investigate the preparation of spin-spin multipartite entanglement, witnessed by quantum Fisher information, by using the cubic nonlinear dynamics. We find that, in the regime of weak coupling, the cubic scheme can greatly speed up the rate of entanglement generation as compared to the quadratic scheme (about $N$ times faster). In the strong coupling regime, the cubic nonlinear dynamics enables the periodic in time generation of a broad variety of new-type macroscopic superposition states, which allow us to realize near-Heisenberg-limit phase sensitivity. In addition, we also reveal an interesting feature that the amount of entanglement generated by the cubic scheme has a macroscopic sensitivity to the parity of $N$, which has no counterpart in quadratic nonlinear dynamics and can be exploited for sensing the parity of $N$ at the single-spin level. We also propose a new approach for a fast and high-fidelity generation of maximally entangled Greenberger-Horne-Zeilinger (GHZ) states. By using an alternative cubic-quadratic-admixture type of nonlinear interaction, we show that one may accelerate the procedure of GHZ-state generation. The realization of the cubic nonlinear dynamics is also considered, showing that the cubic nonlinear dynamics can be realized by either repeatedly using linear- and quadratic-nonlinear dynamics or utilizing light-mediated interactions in just one step. Finally, by taking realistic imperfections into account, we find that the cubic scheme is sensitivity to the single-spin decay in the strong coupling regime, while is robust against the collective dephasing.

quant-ph↗

arXiv2022

A Tribute to Phil Bourne -- Scientist and Human

This Special Issue of Biomolecules, commissioned in honor of Dr. Philip E. Bourne, focuses on a new field of biomolecular data science. In this brief retrospective, we consider the arc of Bourne's 40-year scientific and professional career, particularly as it relates to the origins of this new field.

q-bio.OT↗

arXiv2022

UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis

Text-to-speech (TTS) and singing voice synthesis (SVS) aim at generating high-quality speaking and singing voice according to textual input and music scores, respectively. Unifying TTS and SVS into a single system is crucial to the applications requiring both of them. Existing methods usually suffer from some limitations, which rely on either both singing and speaking data from the same person or cascaded models of multiple tasks. To address these problems, a simplified elegant framework for TTS and SVS, named UniSyn, is proposed in this paper. It is an end-to-end unified model that can make a voice speak and sing with only singing or speaking data from this person. To be specific, a multi-conditional variational autoencoder (MC-VAE), which constructs two independent latent sub-spaces with the speaker- and style-related (i.e. speak or sing) conditions for flexible control, is proposed in UniSyn. Moreover, supervised guided-VAE and timbre perturbation with the Wasserstein distance constraint are leveraged to further disentangle the speaker timbre and style. Experiments conducted on two speakers and two singers demonstrate that UniSyn can generate natural speaking and singing voice without corresponding training data. The proposed approach outperforms the state-of-the-art end-to-end voice generation work, which proves the effectiveness and advantages of UniSyn.

cs.SD↗

arXiv2022

MSV Challenge 2022: NPU-HC Speaker Verification System for Low-resource Indian Languages

This report describes the NPU-HC speaker verification system submitted to the O-COCOSDA Multi-lingual Speaker Verification (MSV) Challenge 2022, which focuses on developing speaker verification systems for low-resource Asian languages. We participate in the I-MSV track, which aims to develop speaker verification systems for various Indian languages. In this challenge, we first explore different neural network frameworks for low-resource speaker verification. Then we leverage vanilla fine-tuning and weight transfer fine-tuning to transfer the out-domain pre-trained models to the in-domain Indian dataset. Specifically, the weight transfer fine-tuning aims to constrain the distance of the weights between the pre-trained model and the fine-tuned model, which takes advantage of the previously acquired discriminative ability from the large-scale out-domain datasets and avoids catastrophic forgetting and overfitting at the same time. Finally, score fusion is adopted to further improve performance. Together with the above contributions, we obtain 0.223% EER on the public evaluation set, ranking 2nd place on the leaderboard. On the private evaluation set, the EER of our submitted system is 2.123% and 0.630% for the constrained and unconstrained sub-tasks of the I-MSV track, leading to the 1st and 3rd place in the ranking, respectively.

eess.AS↗

arXiv2022

TESSP: Text-Enhanced Self-Supervised Speech Pre-training

Self-supervised speech pre-training empowers the model with the contextual structure inherent in the speech signal while self-supervised text pre-training empowers the model with linguistic information. Both of them are beneficial for downstream speech tasks such as ASR. However, the distinct pre-training objectives make it challenging to jointly optimize the speech and text representation in the same model. To solve this problem, we propose Text-Enhanced Self-Supervised Speech Pre-training (TESSP), aiming to incorporate the linguistic information into speech pre-training. Our model consists of three parts, i.e., a speech encoder, a text encoder and a shared encoder. The model takes unsupervised speech and text data as the input and leverages the common HuBERT and MLM losses respectively. We also propose phoneme up-sampling and representation swapping to enable joint modeling of the speech and text information. Specifically, to fix the length mismatching problem between speech and text data, we phonemize the text sequence and up-sample the phonemes with the alignment information extracted from a small set of supervised data. Moreover, to close the gap between the learned speech and text representations, we swap the text representation with the speech representation extracted by the respective private encoders according to the alignment information. Experiments on the Librispeech dataset shows the proposed TESSP model achieves more than 10% improvement compared with WavLM on the test-clean and test-other sets. We also evaluate our model on the SUPERB benchmark, showing our model has better performance on Phoneme Recognition, Acoustic Speech Recognition and Speech Translation compared with WavLM.

cs.SD↗

arXiv2022

Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features

Voice conversion for highly expressive speech is challenging. Current approaches struggle with the balancing between speaker similarity, intelligibility and expressiveness. To address this problem, we propose Expressive-VC, a novel end-to-end voice conversion framework that leverages advantages from both neural bottleneck feature (BNF) approach and information perturbation approach. Specifically, we use a BNF encoder and a Perturbed-Wav encoder to form a content extractor to learn linguistic and para-linguistic features respectively, where BNFs come from a robust pre-trained ASR model and the perturbed wave becomes speaker-irrelevant after signal perturbation. We further fuse the linguistic and para-linguistic features through an attention mechanism, where speaker-dependent prosody features are adopted as the attention query, which result from a prosody encoder with target speaker embedding and normalized pitch and energy of source speech as input. Finally the decoder consumes the integrated features and the speaker-dependent prosody feature to generate the converted speech. Experiments demonstrate that Expressive-VC is superior to several state-of-the-art systems, achieving both high expressiveness captured from the source speech and high speaker similarity with the target speaker; meanwhile intelligibility is well maintained.

eess.AS↗

arXiv2022

Preserving background sound in noise-robust voice conversion via multi-task learning

Background sound is an informative form of art that is helpful in providing a more immersive experience in real-application voice conversion (VC) scenarios. However, prior research about VC, mainly focusing on clean voices, pay rare attention to VC with background sound. The critical problem for preserving background sound in VC is inevitable speech distortion by the neural separation model and the cascade mismatch between the source separation model and the VC model. In this paper, we propose an end-to-end framework via multi-task learning which sequentially cascades a source separation (SS) module, a bottleneck feature extraction module and a VC module. Specifically, the source separation task explicitly considers critical phase information and confines the distortion caused by the imperfect separation process. The source separation task, the typical VC task and the unified task shares a uniform reconstruction loss constrained by joint training to reduce the mismatch between the SS and VC modules. Experimental results demonstrate that our proposed framework significantly outperforms the baseline systems while achieving comparable quality and speaker similarity to the VC models trained with clean data.

eess.AS↗

arXiv2022

Distinguishable Speaker Anonymization based on Formant and Fundamental Frequency Scaling

Speech data on the Internet are proliferating exponentially because of the emergence of social media, and the sharing of such personal data raises obvious security and privacy concerns. One solution to mitigate these concerns involves concealing speaker identities before sharing speech data, also referred to as speaker anonymization. In our previous work, we have developed an automatic speaker verification (ASV)-model-free anonymization framework to protect speaker privacy while preserving speech intelligibility. Although the framework ranked first place in VoicePrivacy 2022 challenge, the anonymization was imperfect, since the speaker distinguishability of the anonymized speech was deteriorated. To address this issue, in this paper, we directly model the formant distribution and fundamental frequency (F0) to represent speaker identity and anonymize the source speech by the uniformly scaling formant and F0. By directly scaling the formant and F0, the speaker distinguishability degradation of the anonymized speech caused by the introduction of other speakers is prevented. The experimental results demonstrate that our proposed framework can improve the speaker distinguishability and significantly outperforms our previous framework in voice distinctiveness. Furthermore, our proposed method also can trade off the privacy-utility by using different scaling factors.

eess.AS↗

arXiv2022

VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer

End-to-end singing voice synthesis (SVS) model VISinger can achieve better performance than the typical two-stage model with fewer parameters. However, VISinger has several problems: text-to-phase problem, the end-to-end model learns the meaningless mapping of text-to-phase; glitches problem, the harmonic components corresponding to the periodic signal of the voiced segment occurs a sudden change with audible artefacts; low sampling rate, the sampling rate of 24KHz does not meet the application needs of high-fidelity generation with the full-band rate (44.1KHz or higher). In this paper, we propose VISinger 2 to address these issues by integrating the digital signal processing (DSP) methods with VISinger. Specifically, inspired by recent advances in differentiable digital signal processing (DDSP), we incorporate a DSP synthesizer into the decoder to solve the above issues. The DSP synthesizer consists of a harmonic synthesizer and a noise synthesizer to generate periodic and aperiodic signals, respectively, from the latent representation z in VISinger. It supervises the posterior encoder to extract the latent representation without phase information and avoid the prior encoder modelling text-to-phase mapping. To avoid glitch artefacts, the HiFi-GAN is modified to accept the waveforms generated by the DSP synthesizer as a condition to produce the singing voice. Moreover, with the improved waveform decoder, VISinger 2 manages to generate 44.1kHz singing audio with richer expression and better quality. Experiments on OpenCpop corpus show that VISinger 2 outperforms VISinger, CpopSing and RefineSinger in both subjective and objective metrics.

cs.SD↗

arXiv2022

The ISCSLP 2022 Intelligent Cockpit Speech Recognition Challenge (ICSRC): Dataset, Tracks, Baseline and Results

This paper summarizes the outcomes from the ISCSLP 2022 Intelligent Cockpit Speech Recognition Challenge (ICSRC). We first address the necessity of the challenge and then introduce the associated dataset collected from a new-energy vehicle (NEV) covering a variety of cockpit acoustic conditions and linguistic contents. We then describe the track arrangement and the baseline system. Specifically, we set up two tracks in terms of allowed model/system size to investigate resource-constrained and -unconstrained setups, targeting to vehicle embedded as well as cloud ASR systems respectively. Finally we summarize the challenge results and provide the major observations from the submitted systems.

cs.SD↗

arXiv2022

AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation

Speaker adaptation in text-to-speech synthesis (TTS) is to finetune a pre-trained TTS model to adapt to new target speakers with limited data. While much effort has been conducted towards this task, seldom work has been performed for low computational resource scenarios due to the challenges raised by the requirement of the lightweight model and less computational complexity. In this paper, a tiny VITS-based TTS model, named AdaVITS, for low computing resource speaker adaptation is proposed. To effectively reduce parameters and computational complexity of VITS, an iSTFT-based wave construction decoder is proposed to replace the upsampling-based decoder which is resource-consuming in the original VITS. Besides, NanoFlow is introduced to share the density estimate across flow blocks to reduce the parameters of the prior encoder. Furthermore, to reduce the computational complexity of the textual encoder, scaled-dot attention is replaced with linear attention. To deal with the instability caused by the simplified model, instead of using the original text encoder, phonetic posteriorgram (PPG) is utilized as linguistic feature via a text-to-PPG module, which is then used as input for the encoder. Experiment shows that AdaVITS can generate stable and natural speech in speaker adaptation with 8.97M model parameters and 0.72GFlops computational complexity.

cs.SD↗

arXiv2022

Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS

In current two-stage neural text-to-speech (TTS) paradigm, it is ideal to have a universal neural vocoder, once trained, which is robust to imperfect mel-spectrogram predicted from the acoustic model. To this end, we propose Robust MelGAN vocoder by solving the original multi-band MelGAN's metallic sound problem and increasing its generalization ability. Specifically, we introduce a fine-grained network dropout strategy to the generator. With a specifically designed over-smooth handler which separates speech signal intro periodic and aperiodic components, we only perform network dropout to the aperodic components, which alleviates metallic sounding and maintains good speaker similarity. To further improve generalization ability, we introduce several data augmentation methods to augment fake data in the discriminator, including harmonic shift, harmonic noise and phase noise. Experiments show that Robust MelGAN can be used as a universal vocoder, significantly improving sound quality in TTS systems built on various types of data.

cs.SD↗

arXiv2022

Intelligent Reflecting Surface-Aided Maneuvering Target Sensing: True Velocity Estimation

Maneuvering target sensing will be an important service of future vehicular networks, where precise velocity estimation is one of the core tasks. To this end, the recently proposed integrated sensing and communications (ISAC) provides a promising platform for achieving accurate velocity estimation. However, with one mono-static ISAC base station (BS), only the radial projection of the true velocity can be estimated, which causes serious estimation error. In this paper, we investigate the estimation of the true velocity of a maneuvering target with the assistance of an intelligent reflecting surface (IRS). We propose an efficient velocity estimation algorithm by exploiting the two perspectives from the BS and IRS to the target. We propose a two-stage scheme where the true velocity can be recovered based on the Doppler frequency of the BS-target link and BS-IRS-target link. Experimental results validate that the true velocity can be precisely recovered and demonstrate the advantage of adding the IRS.

eess.SP↗

arXiv2022

AccentSpeech: Learning Accent from Crowd-sourced Data for Target Speaker TTS with Accents

Learning accent from crowd-sourced data is a feasible way to achieve a target speaker TTS system that can synthesize accent speech. To this end, there are two challenging problems to be solved. First, direct use of the poor acoustic quality crowd-sourced data and the target speaker data in accent transfer will apparently lead to synthetic speech with degraded quality. To mitigate this problem, we take a bottleneck feature (BN) based TTS approach, in which TTS is decomposed into a Text-to-BN (T2BN) module to learn accent and a BN-to-Mel (BN2Mel) module to learn speaker timbre, where neural network based BN feature serves as the intermediate representation that are robust to noise interference. Second, direct training T2BN using the crowd-sourced data in the two-stage system will produce accent speech of target speaker with poor prosody. This is because the the crowd-sourced recordings are contributed from the ordinary unprofessional speakers. To tackle this problem, we update the two-stage approach to a novel three-stage approach, where T2BN and BN2Mel are trained using the high-quality target speaker data and a new BN-to-BN module is plugged in between the two modules to perform accent transfer. To train the BN2BN module, the parallel unaccented and accented BN features are obtained by a proposed data augmentation procedure. Finally the proposed three-stage approach manages to produce accent speech for the target speaker with good prosody, as the prosody pattern is inherited from the professional target speaker and accent transfer is achieved by the BN2BN module at the same time. The proposed approach, named as AccentSpeech, is validated in a Mandarin TTS accent transfer task.

cs.SD↗