Search

Despite recent advancements in speech generation with text prompt providing control over speech style, voice attributes in synthesized speech remain elusive and challenging to control. This paper introduces a novel task: voice attribute editing with text prompt, with the goal of making relative modifications to voice attributes according to the actions described in the text prompt. To solve this task, VoxEditor, an end-to-end generative model, is proposed. In VoxEditor, addressing the insufficiency of text prompt, a Residual Memory (ResMem) block is designed, that efficiently maps voice attributes and these descriptors into the shared feature space. Additionally, the ResMem block is enhanced with a voice attribute degree prediction (VADP) block to align voice attributes with corresponding descriptors, addressing the imprecision of text prompt caused by non-quantitative descriptions of voice attributes. We also establish the open-source VCTK-RVA dataset, which leads the way in manual annotations detailing voice characteristic differences among different speakers. Extensive experiments demonstrate the effectiveness and generalizability of our proposed method in terms of both objective and subjective metrics. The dataset and audio samples are available on the website.

We study the $B^- \to K^- \eta \eta_c$ decay by taking into account the $S$-wave contributions from the pseudoscalar meson-pseudoscalar meson interactions within the unitary coupled-channel approach, where the $D\bar{D}$ bound state is dynamically generated. In addition, the contribution from the intermediate resonance $K_0^*(1430)^-$, with $K_0^*(1430)^- \to K^-\eta$, is also considered. Our results show that there is a clear peak around $3720$~MeV in the $\eta \eta_c$ invariant mass distribution, which could be associated with the $D \bar{D}$ bound state. The future precise measurements of the $B^- \to K^- \eta \eta_c$ process at the Belle II and LHCb experiments could be, therefore, used to check the existence of the $D \bar{D}$ bound state, and to deepen our understanding of the hadron-hadron interactions., Comment: 14 pages, 9 figures

Based on the BESIII measurements on the reaction of $D_s^+\to \pi^+\pi^0\pi^0$, we investigate this process by considering the $S$-wave pseudoscalar-pseudoscalar interaction within the unitary chiral approach, and the contributions from the intermediate resonances $f_0(1370)$ and $f_2(1270)$. Our calculation could reasonably reproduce the experimental data, and our results imply that the $f_0(980)$, dynamically generated from the $S$-wave pseudoscalar-pseudoscalar interaction, plays an important role in this process, and the contributions from the intermediate resonances $f_0(1370)$ and $f_2(1270)$ are also necessary. The more precise measurements of this process in future could shed light on the nature of the $f_0(1370)$ and $f_2(1270)$., Comment: 7 pages, 4 figures

In this work, we calculate the mass spectrum of the bottom mesons with a modified nonrelativistic quark model by involving the screening effect, and explore their strong decay properties within the $^3P_0$ model. Our results suggest that the $B_1(5721)$, $B^*_2(5747)$, $B_J(5840)$, and $B_J(5970)$ could be reasonably assigned as the $B_1^\prime(1P)$, $B(1^3P_2)$, $B(2^1S_0)$, and $B(1^3D_3)$ respectively. The more precise measurements of the excited bottom mesons are crucial to confirm these assignments., Comment: 6 pages, 2 figures

In this work, we have investigated the process $D_s^+\to K^+ K^- \pi^+$, taking into account the contributions from the $S$-wave pseudoscalar-pseudoscalar interaction within the chiral unitary approach, and also the intermediate $\phi$ resonance. By analyzing the BESIII and {\it BABAR} measurements, we conclude that the $f_0(980)$ state, dynamically generated from the $S$-wave pseudoscalar-pseudoscalar interaction, gives the dominant contribution close to the $K^+K^-$ threshold in the $K^+K^-$ invariant mass distribution of the decay $D_s^+\to K^+ K^- \pi^+$ in $S$-wave. On the other hand, our results imply that the lineshape adopted by BESIII and {\it BABAR} for the resonances $a_0(980)$ and $f_0(980)$ is not advisable in the fit to the data close to the $K^+K^-$ threshold., Comment: 9 pages, 9 figures, 1 table, Published in Phys.Lett.B 821(2021)136617

With the development of automatic speech recognition (ASR) and text-to-speech synthesis (TTS) technique, it's intuitive to construct a voice conversion system by cascading an ASR and TTS system. In this paper, we present a ASR-TTS method for voice conversion, which used iFLYTEK ASR engine to transcribe the source speech into text and a Transformer TTS model with WaveNet vocoder to synthesize the converted speech from the decoded text. For the TTS model, we proposed to use a prosody code to describe the prosody information other than text and speaker information contained in speech. A prosody encoder is used to extract the prosody code. During conversion, the source prosody is transferred to converted speech by conditioning the Transformer TTS model with its code. Experiments were conducted to demonstrate the effectiveness of our proposed method. Our system also obtained the best naturalness and similarity in the mono-lingual task of Voice Conversion Challenge 2020., Comment: Submitted to Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020, INTERSPEECH 2020

With the advantages of both classical and quantum secret sharing, many practical hybrid quantum secret sharing have been proposed. In this paper, we propose a hybrid quantum secret sharing scheme based on mutually unbiased bases and monotone span program. First, the dealer sends the shares in the linear secret sharing to the participants in the authorization set via a secure channel. Then, the dealer and participants perform unitary transformation on a d-dimensional quantum state sequentially, and the dealer publishes the measurement result confidentially to the participants in the authorization set to recover the secret. The verifiability of the scheme is guaranteed by the Hash function. Next, the correctness and security of the scheme are proved and our scheme is secure against the general eavesdropper attacks. Finally, a specific example is employed to further clarify the exibility of the scheme and the detailed comparison of similar quantum secret sharing schemes also shows the superiority of our proposed scheme., Comment: 13 pages, 2 figures

Quantum key agreement requires all participants to recover the shared key together, so it is crucial to resist the participant attack. In this paper, we propose a verifiable multi-party quantum key agreement protocol based on the six-qubit cluster states. A verifiable distributor who preserves some subsequences of the six-qubit cluster states is introduced into this protocol, thus the participants can not obtain the shared key in advance. Besides, the correctness and simultaneity of the shared key are guaranteed by the trusted design combiner and homomorphic hash function. Furthermore, the security analysis shows that the new protocol can resist the external and internal attacks., Comment: 9 pages, 2 figures

In the $\left( {t,n} \right)$ threshold quantum secret sharing scheme, it is difficult to ensure that internal participants are honest. In this paper, a verifiable $\left( {t,n} \right)$ threshold quantum secret sharing scheme is designed combined with classical secret sharing scheme. First of all, the distributor uses the asymmetric binary polynomials to generate the shares and sends them to each participant. Secondly, the distributor sends the initial quantum state with the secret to the first participant, and each participant performs unitary operation that using the mutually unbiased bases on the obtained $d$ dimension single bit quantum state ($d$ is a large odd prime number). In this process, distributor can randomly check the participants, and find out the internal fraudsters by unitary inverse operation gradually upward. Then the secret is reconstructed after all other participants simultaneously public transmission. Security analysis show that this scheme can resist both external and internal attacks.

To detect frauds from some internal participants or external attackers, some verifiable threshold quantum secret sharing schemes have been proposed. In this paper, we present a new verifiable threshold structure based on a single qubit using bivariate polynomial. First, Alice chooses an asymmetric bivariate polynomial and sends a pair of values from this polynomial to each participant. Then Alice and participants implement in sequence unitary transformation on the $d$-dimensional quantum state based on unbiased bases, where those unitary transformations are contacted by this polynomial. Finally, security analysis shows that the proposed scheme can detect the fraud from external and internal attacks compared with the exiting schemes and is comparable to the recent schemes.

Automatic speaker verification (ASV) is one of the most natural and convenient means of biometric person recognition. Unfortunately, just like all other biometric systems, ASV is vulnerable to spoofing, also referred to as "presentation attacks." These vulnerabilities are generally unacceptable and call for spoofing countermeasures or "presentation attack detection" systems. In addition to impersonation, ASV systems are vulnerable to replay, speech synthesis, and voice conversion attacks. The ASVspoof 2019 edition is the first to consider all three spoofing attack types within a single challenge. While they originate from the same source database and same underlying protocol, they are explored in two specific use case scenarios. Spoofing attacks within a logical access (LA) scenario are generated with the latest speech synthesis and voice conversion technologies, including state-of-the-art neural acoustic and waveform model techniques. Replay spoofing attacks within a physical access (PA) scenario are generated through carefully controlled simulations that support much more revealing analysis than possible previously. Also new to the 2019 edition is the use of the tandem detection cost function metric, which reflects the impact of spoofing and countermeasures on the reliability of a fixed ASV system. This paper describes the database design, protocol, spoofing attack implementations, and baseline ASV and countermeasure results. It also describes a human assessment on spoofed data in logical access. It was demonstrated that the spoofing data in the ASVspoof 2019 database have varied degrees of perceived quality and similarity to the target speakers, including spoofed data that cannot be differentiated from bona-fide utterances even by human subjects., Comment: Accepted, Computer Speech and Language. This manuscript version is made available under the CC-BY-NC-ND 4.0. For the published version on Elsevier website, please visit https://doi.org/10.1016/j.csl.2020.101114

This paper proposes an end-to-end emotional speech synthesis (ESS) method which adopts global style tokens (GSTs) for semi-supervised training. This model is built based on the GST-Tacotron framework. The style tokens are defined to present emotion categories. A cross entropy loss function between token weights and emotion labels is designed to obtain the interpretability of style tokens utilizing the small portion of training data with emotion labels. Emotion recognition experiments confirm that this method can achieve one-to-one correspondence between style tokens and emotion categories effectively. Objective and subjective evaluation results show that our model outperforms the conventional Tacotron model for ESS when only 5\% of training data has emotion labels. Its subjective performance is close to the Tacotron model trained using all emotion labels., Comment: 5 pages, 2 figures submitted to APSIPA2019

This paper presents methods of making using of text supervision to improve the performance of sequence-to-sequence (seq2seq) voice conversion. Compared with conventional frame-to-frame voice conversion approaches, the seq2seq acoustic modeling method proposed in our previous work achieved higher naturalness and similarity. In this paper, we further improve its performance by utilizing the text transcriptions of parallel training data. First, a multi-task learning structure is designed which adds auxiliary classifiers to the middle layers of the seq2seq model and predicts linguistic labels as a secondary task. Second, a data-augmentation method is proposed which utilizes text alignment to produce extra parallel sequences for model training. Experiments are conducted to evaluate our proposed method with training sets at different sizes. Experimental results show that the multi-task learning with linguistic labels is effective at reducing the errors of seq2seq voice conversion. The data-augmentation method can further improve the performance of seq2seq voice conversion when only 50 or 100 training utterances are available., Comment: 5 pages, 4 figures, 2 tables. Submitted to IEEE ICASSP 2019

In this paper, a neural network named Sequence-to-sequence ConvErsion NeTwork (SCENT) is presented for acoustic modeling in voice conversion. At training stage, a SCENT model is estimated by aligning the feature sequences of source and target speakers implicitly using attention mechanism. At conversion stage, acoustic features and durations of source utterances are converted simultaneously using the unified acoustic model. Mel-scale spectrograms are adopted as acoustic features which contain both excitation and vocal tract descriptions of speech signals. The bottleneck features extracted from source speech using an automatic speech recognition (ASR) model are appended as auxiliary input. A WaveNet vocoder conditioned on Mel-spectrograms is built to reconstruct waveforms from the outputs of the SCENT model. It is worth noting that our proposed method can achieve appropriate duration conversion which is difficult in conventional methods. Experimental results show that our proposed method obtained better objective and subjective performance than the baseline methods using Gaussian mixture models (GMM) and deep neural networks (DNN) as acoustic models. This proposed method also outperformed our previous work which achieved the top rank in Voice Conversion Challenge 2018. Ablation tests further confirmed the effectiveness of several components in our proposed method., Comment: Published on IEEE/ACM Transactions on Audio, Speech and Language Processing

We have performed a theoretical study on the process $\chi_{c0}(1P)\to \bar{\Lambda}\Sigma\pi$, by taking into account the final state interactions of $\pi\Sigma$ and $\pi\bar{\Lambda}$ based on the chiral unitary approach. As the isospin filters of $I=0$ in the $\pi\Sigma$ channel and $I=1$ in the $\pi\bar{\Lambda}$ channel, this process can be used to study the molecular structure of the $\Lambda(1405)$ resonance, and to test the existence of the predicted states $\Sigma(1380)$ and $\Sigma(1430)$ with spin-parity $J^P=1/2^-$. Our results show that there is a peak around $1350 \sim 1400$~MeV, and a cusp around the $\bar{K}N$ threshold in the $\pi\Sigma$ invariant mass distribution, which should be the important feature of the molecular state $\Lambda(1405)$. We also find a peak around $1380$~MeV, and a cusp around $\bar{K}N$ threshold in the $\pi\bar{\Lambda}$ invariant mass distribution, which are associated to the $\Sigma(1380)$ and $\Sigma(1430)$ resonances., Comment: 7 pages, 13 figures, the version for PRD

The production of the $f_1(1285)$ resonance in the reaction of $\gamma p \rightarrow f_1(1285) p$ is investigated within a Regge-effective Lagrangian approach. Besides the contributions of the $t$-channel $\rho$ and $\omega$ trajectories exchanges, we also take into account the contributions of $s/u$-channel $N(2300)$ terms, $s/u$-channel nucleon terms, and the contact term. By fitting to the CLAS data, we find that the $s$-channel $N(2300)$ term plays an important role in this reaction. We predict the total cross section for this reaction, and find a clear bump structure around $W=2.3$ GeV, which is associated with the $N(2300)$ state. The reaction of $\gamma p \to f_1(1285) p$ could be useful to further study of the $N(2300)$ experimentally., Comment: 6 pages, 5 figures, version accepted by Phys. Rev. D