Search

Model editing is a technique that edits the large language models (LLMs) with updated knowledge to alleviate hallucinations without resource-intensive retraining. While current model editing methods can effectively modify a model's behavior within a specific area of interest, they often overlook the potential unintended side effects on the general abilities of LLMs such as reasoning, natural language inference, and question answering. In this paper, we raise concerns that model editing's improvements on factuality may come at the cost of a significant degradation of the model's general abilities. We systematically analyze the side effects by evaluating four popular editing methods on three LLMs across eight representative tasks. Our extensive empirical experiments show that it is challenging for current editing methods to simultaneously improve factuality of LLMs and maintain their general abilities. Our analysis reveals that the side effects are caused by model editing altering the original model weights excessively, leading to overfitting to the edited facts. To mitigate this, a method named RECT is proposed to regularize the edit update weights by imposing constraints on their complexity based on the RElative Change in weighT. Evaluation results show that RECT can significantly mitigate the side effects of editing while still maintaining over 94% editing performance., Comment: Accepted by EMNLP 2024

While several long-form VideoQA datasets have been introduced, the length of both videos used to curate questions and sub-clips of clues leveraged to answer those questions have not yet reached the criteria for genuine long-form video understanding. Moreover, their QAs are unduly narrow and modality-biased, lacking a wider view of understanding long-term video content with rich dynamics and complex narratives. To remedy this, we introduce MoVQA, a long-form movie question-answering dataset, and benchmark to assess the diverse cognitive capabilities of multimodal systems rely on multi-level temporal lengths, with considering both video length and clue length. Additionally, to take a step towards human-level understanding in long-form video, versatile and multimodal question-answering is designed from the moviegoer-perspective to assess the model capabilities on various perceptual and cognitive axes.Through analysis involving various baselines reveals a consistent trend: the performance of all methods significantly deteriorate with increasing video and clue length. Meanwhile, our established baseline method has shown some improvements, but there is still ample scope for enhancement on our challenging MoVQA dataset. We expect our MoVQA to provide a new perspective and encourage inspiring works on long-form video understanding research.

In this work, we investigate the isospin breaking decay $X_b \to \pi^0\chi_{bJ}$ and the isospin conserved decay $X_b \to \pi\pi\chi_{bJ}$, where $X_b$ is taken to be the heavy quark flavor symmetry counterpart of $X(3872)$ in the bottomonium sector as a $B^*\bar B$ molecule candidate. Since the mass of this state may be far below the $B {\bar B}^*$ threshold and the mass difference between the neutral and charged bottom meson is small compared to the binding energy of the $X_b$, the isospin-violating decay channel $X_b \to \pi^0 \chi_{bJ}$ would be highly suppressed. The calculated partial width of $X_b \to \pi\pi\chi_{b1}$ is found to be about tens of $\rm{keVs}$, $1\sim 2$ order(s) of magnitude larger than those of $X_b \to \pi\pi\chi_{b2}$ and $X_b \to \pi\pi\chi_{b0}$. Taking into account the fact that the total width of $X_b$ may be smaller than a few MeV like $X(3872)$, the calculated branching ratios $X_b\to \pi\pi \chi_{b1}$ may reach to orders of $10^{-2}$, which makes it a possible channel for the experimental searching of the $X_b$., Comment: 14 pages, 5 figures, published in Phys.Rev.D

Speech enhancement is widely used as a front-end to improve the speech quality in many audio systems, while it is hard to extract the target speech in multi-talker conditions without prior information on the speaker identity. It was shown that the auditory attention on the target speaker can be decoded from the electroencephalogram (EEG) of the listener implicitly. In this work, we therefore propose a novel end-to-end brain-assisted speech enhancement network (BASEN), which incorporates the listeners' EEG signals and adopts a temporal convolutional network together with a convolutional multi-layer cross attention module to fuse EEG-audio features. Considering that an EEG cap with sparse channels exhibits multiple benefits and in practice many electrodes might contribute marginally, we further propose two channel selection methods, called residual Gumbel selection and convolutional regularization selection. They are dedicated to tackling training instability and duplicated channel selections, respectively. Experimental results on a public dataset show the superiority of the proposed BASEN over existing approaches. The proposed channel selection methods can significantly reduce the amount of informative EEG channels with a negligible impact on the performance., Comment: arXiv admin note: text overlap with arXiv:2305.09994

In our previous work, we proposed a neural vocoder called APNet, which directly predicts speech amplitude and phase spectra with a 5 ms frame shift in parallel from the input acoustic features, and then reconstructs the 16 kHz speech waveform using inverse short-time Fourier transform (ISTFT). APNet demonstrates the capability to generate synthesized speech of comparable quality to the HiFi-GAN vocoder but with a considerably improved inference speed. However, the performance of the APNet vocoder is constrained by the waveform sampling rate and spectral frame shift, limiting its practicality for high-quality speech synthesis. Therefore, this paper proposes an improved iteration of APNet, named APNet2. The proposed APNet2 vocoder adopts ConvNeXt v2 as the backbone network for amplitude and phase predictions, expecting to enhance the modeling capability. Additionally, we introduce a multi-resolution discriminator (MRD) into the GAN-based losses and optimize the form of certain losses. At a common configuration with a waveform sampling rate of 22.05 kHz and spectral frame shift of 256 points (i.e., approximately 11.6ms), our proposed APNet2 vocoder outperformed the original APNet and Vocos vocoders in terms of synthesized speech quality. The synthesized speech quality of APNet2 is also comparable to that of HiFi-GAN and iSTFTNet, while offering a significantly faster inference speed.

Large Language Models (LLMs) have emerged as influential instruments within the realm of natural language processing; nevertheless, their capacity to handle multi-party conversations (MPCs) -- a scenario marked by the presence of multiple interlocutors involved in intricate information exchanges -- remains uncharted. In this paper, we delve into the potential of generative LLMs such as ChatGPT and GPT-4 within the context of MPCs. An empirical analysis is conducted to assess the zero-shot learning capabilities of ChatGPT and GPT-4 by subjecting them to evaluation across three MPC datasets that encompass five representative tasks. The findings reveal that ChatGPT's performance on a number of evaluated MPC tasks leaves much to be desired, whilst GPT-4's results portend a promising future. Additionally, we endeavor to bolster performance through the incorporation of MPC structures, encompassing both speaker and addressee architecture. This study provides an exhaustive evaluation and analysis of applying generative LLMs to MPCs, casting a light upon the conception and creation of increasingly effective and robust MPC agents. Concurrently, this work underscores the challenges implicit in the utilization of LLMs for MPCs, such as deciphering graphical information flows and generating stylistically consistent responses., Comment: Accepted by Findings of EMNLP 2023

In this paper, some subtleties in the measurement of the transverse polarization of the produced hadrons on symmetric colliders -- such as the Large Hadron Collider when conducting the $pp$ collisions -- are revealed. It can be proved that the transverse polarization of the produced particles with opposite pseudorapidity takes exactly opposite values if the normal vector of the production plane is defined in a convention-dependent way, regardless of whether parity is conserved or not in the production process. The analysis shows that, due to the symmetry of the initial state, the $\Lambda_b$ transverse polarization measured by the CMS collaboration in Phys. Rev. D 97, 072010 (2018) should be exactly equal to zero. A modified measurement of the $\Lambda_b$ polarization for CMS and ATLAS is proposed, the result of which can be compared to the LHCb measurement., Comment: Accepted by Phys. Rev. D, 4 pages, 1 figure (with 2 subfigures)

Recent studies have demonstrated that large language models (LLMs) store massive factual knowledge within their parameters. But existing LLMs are prone to hallucinate unintended text due to false or outdated knowledge. Since retraining LLMs is resource intensive, there has been a growing interest in the concept of model editing. Despite the emergence of benchmarks and approaches, these unidirectional editing and evaluation have failed to explore the reversal curse. Intuitively, if "The capital of France is" is edited to be a counterfact "London" within a model, then it should be able to naturally reason and recall the reverse fact, i.e., "London is the capital of" followed by "France" instead of "England". In this paper, we study bidirectional language model editing, aiming to provide rigorous model editing evaluation to assess if edited LLMs can recall the editing knowledge bidirectionally. A new evaluation metric of reversibility is introduced, and a benchmark dubbed as Bidirectional Assessment for Knowledge Editing (BAKE) is constructed to evaluate the reversibility of edited models in recalling knowledge in the reverse direction of editing. We surprisingly observe that while current editing methods and LLMs can effectively recall editing facts in the direction of editing, they suffer serious deficiencies when evaluated in the reverse direction. To mitigate the reversal curse, a method named Bidirectionally Inversible Relationship moDeling (BIRD) is proposed. A set of editing objectives that incorporate bidirectional relationships between subject and object into the updated model weights are designed. Experiments show that BIRD improves the performance of four representative LLMs of different sizes via question answering and judgement.

Synchrotron-based angle-resolved photoemission spectroscopy was employed to investigate the temperature evolution of the Yb 4f spectral for surface and bulk in the Kondo lattice YbCu$_2$Si$_2$.Our study quantitatively distinguishes between the surface and bulk hybridization processes, revealing that the onset temperatures for both surface and bulk hybridization processes are significantly higher than the Kondo temperature. Additionally, we found that the effective surface Kondo temperature is much lower than that of the bulk. These findings offer valuable insights into the understanding of heavy fermion physics., Comment: 7 pages, 4 figures

Audio-visual speech enhancement (AV-SE) aims to enhance degraded speech along with extra visual information such as lip videos, and has been shown to be more effective than audio-only speech enhancement. This paper proposes the incorporation of ultrasound tongue images to improve the performance of lip-based AV-SE systems further. To address the challenge of acquiring ultrasound tongue images during inference, we first propose to employ knowledge distillation during training to investigate the feasibility of leveraging tongue-related information without directly inputting ultrasound tongue images. Specifically, we guide an audio-lip speech enhancement student model to learn from a pre-trained audio-lip-tongue speech enhancement teacher model, thus transferring tongue-related knowledge. To better model the alignment between the lip and tongue modalities, we further propose the introduction of a lip-tongue key-value memory network into the AV-SE model. This network enables the retrieval of tongue features based on readily available lip features, thereby assisting the subsequent speech enhancement task. Experimental results demonstrate that both methods significantly improve the quality and intelligibility of the enhanced speech compared to traditional lip-based AV-SE baselines. Moreover, both proposed methods exhibit strong generalization performance on unseen speakers and in the presence of unseen noises. Furthermore, phone error rate (PER) analysis of automatic speech recognition (ASR) reveals that while all phonemes benefit from introducing ultrasound tongue images, palatal and velar consonants benefit most., Comment: Submmited to IEEE/ACM Transactions on Audio, Speech and Language Processing. arXiv admin note: text overlap with arXiv:2305.14933

This paper presents a novel task, zero-shot voice conversion based on face images (zero-shot FaceVC), which aims at converting the voice characteristics of an utterance from any source speaker to a newly coming target speaker, solely relying on a single face image of the target speaker. To address this task, we propose a face-voice memory-based zero-shot FaceVC method. This method leverages a memory-based face-voice alignment module, in which slots act as the bridge to align these two modalities, allowing for the capture of voice characteristics from face images. A mixed supervision strategy is also introduced to mitigate the long-standing issue of the inconsistency between training and inference phases for voice conversion tasks. To obtain speaker-independent content-related representations, we transfer the knowledge from a pretrained zero-shot voice conversion model to our zero-shot FaceVC model. Considering the differences between FaceVC and traditional voice conversion tasks, systematic subjective and objective metrics are designed to thoroughly evaluate the homogeneity, diversity and consistency of voice characteristics controlled by face images. Through extensive experiments, we demonstrate the superiority of our proposed method on the zero-shot FaceVC task. Samples are presented on our demo website.

We investigate the transport properties within a holographic model characterized by a novel gauge-axion coupling. A key innovation is the introduction of the direct coupling between axion fields, the antisymmetric tensor, and the gauge field in our bulk theory. This novel coupling term leads to the emergence of nondiagonal components in the conductivity tensor. An important characteristic is that the off-diagonal elements manifest antisymmetry. Remarkably, the conductivity behavior in this model akin to that of Hall conductivity. Additionally, this model can also achieve metal-insulator transition., Comment: 29 pages, 11 figures, Published version

Phase information has a significant impact on speech perceptual quality and intelligibility. However, existing speech enhancement methods encounter limitations in explicit phase estimation due to the non-structural nature and wrapping characteristics of the phase, leading to a bottleneck in enhanced speech quality. To overcome the above issue, in this paper, we proposed MP-SENet, a novel Speech Enhancement Network that explicitly enhances Magnitude and Phase spectra in parallel. The proposed MP-SENet comprises a Transformer-embedded encoder-decoder architecture. The encoder aims to encode the input distorted magnitude and phase spectra into time-frequency representations, which are further fed into time-frequency Transformers for alternatively capturing time and frequency dependencies. The decoder comprises a magnitude mask decoder and a phase decoder, directly enhancing magnitude and wrapped phase spectra by incorporating a magnitude masking architecture and a phase parallel estimation architecture, respectively. Multi-level loss functions explicitly defined on the magnitude spectra, wrapped phase spectra, and short-time complex spectra are adopted to jointly train the MP-SENet model. A metric discriminator is further employed to compensate for the incomplete correlation between these losses and human auditory perception. Experimental results demonstrate that our proposed MP-SENet achieves state-of-the-art performance across multiple speech enhancement tasks, including speech denoising, dereverberation, and bandwidth extension. Compared to existing phase-aware speech enhancement methods, it further mitigates the compensation effect between the magnitude and phase by explicit phase estimation, elevating the perceptual quality of enhanced speech., Comment: Submmited to IEEE Transactions on Audio, Speech and Language Processing

Speech phase prediction, which is a significant research focus in the field of signal processing, aims to recover speech phase spectra from amplitude-related features. However, existing speech phase prediction methods are constrained to recovering phase spectra with short frame shifts, which are considerably smaller than the theoretical upper bound required for exact waveform reconstruction of short-time Fourier transform (STFT). To tackle this issue, we present a novel long-frame-shift neural speech phase prediction (LFS-NSPP) method which enables precise prediction of long-frame-shift phase spectra from long-frame-shift log amplitude spectra. The proposed method consists of three stages: interpolation, prediction and decimation. The short-frame-shift log amplitude spectra are first constructed from long-frame-shift ones through frequency-by-frequency interpolation to enhance the spectral continuity, and then employed to predict short-frame-shift phase spectra using an NSPP model, thereby compensating for interpolation errors. Ultimately, the long-frame-shift phase spectra are obtained from short-frame-shift ones through frame-by-frame decimation. Experimental results show that the proposed LFS-NSPP method can yield superior quality in predicting long-frame-shift phase spectra than the original NSPP model and other signal-processing-based phase estimation algorithms., Comment: Published at IEEE Signal Processing Letters

We study the parameters range for the fixed point of a class of complex dynamics with the rational fractional function as $R_{n,a,c}(z)=z^n+\frac{a}{z^n}+c$, where $n=1,2,3,4$ is specified, $a$ and $c$ are two complex parameters. The relationship between two parameters, $a$ and $c$, is obtained at the fixed point. Moreover the explicit expression of the parameter $a$ and $c$ in terms of $\lambda$ is derived, where $\lambda$ is the derivative function at fixed point. The parameter regimes for the stability of the fixed point are presented numerically for some typical different cases., Comment: 15 pages, 6 figures

With the assumptions that the $T_{cc}^+$ discovered at LHCb is a $D^{*}D$ hadronic molecule, using a nonrelativistic effective field theory we calculate the radiative partial widths of $T_{cc}^* \to D^*D\gamma$ with $T_{cc}^*$ being a $D^{*}D^{*}$ shallow bound state and the heavy-quark-spin partner of $T_{cc}^+$. The $I=0$ $D^*D$ rescattering effect with the $T_{cc}$ pole is taken into account. The results show that the isoscalar $D^{\ast} D$ rescattering can increase the tree-level decay width of $T_{cc}^{\ast +}\rightarrow D^{*+}D^0\gamma$ by about $50\%$, while decrease that of $T_{cc}^{\ast +}\rightarrow D^{*0}D^+\gamma$ by a similar amount. The two-body partial decay widths of the $T_{cc}^{*+}$ into $T_{cc}^+\gamma$ and $T_{cc}^+\pi^0$ are also calculated, and the results are about $6~\rm{keV}$ and $3~\rm{keV}$, respectively. Considering that the $D^*$ needs to be reconstructed from the $D\pi$ or $D\gamma$ final state in an experimental measurement, the four-body partial widths of the $T_{cc}^{*+}$ into $DD\gamma\gamma$ and $DD\pi\gamma$ are explicitly calculated, and we find that the interference effect between different intermediate $D^*D\gamma$ states is small. The total radiative decay width of the $T_{cc}^*$ is predicted to be about $24~\rm{keV}$. Adding the hadronic decay widths of $T_{cc}^* \to D^*D\pi$, the total width of the $T_{cc}^*$ is finally predicted to be $(65\pm2)$ keV., Comment: 27 pages, 13 figures. arXiv admin note: text overlap with arXiv:2211.02479

Audio-visual speech enhancement (AV-SE) aims to enhance degraded speech along with extra visual information such as lip videos, and has been shown to be more effective than audio-only speech enhancement. This paper proposes further incorporating ultrasound tongue images to improve lip-based AV-SE systems' performance. Knowledge distillation is employed at the training stage to address the challenge of acquiring ultrasound tongue images during inference, enabling an audio-lip speech enhancement student model to learn from a pre-trained audio-lip-tongue speech enhancement teacher model. Experimental results demonstrate significant improvements in the quality and intelligibility of the speech enhanced by the proposed method compared to the traditional audio-lip speech enhancement baselines. Further analysis using phone error rates (PER) of automatic speech recognition (ASR) shows that palatal and velar consonants benefit most from the introduction of ultrasound tongue images., Comment: Published in InterSpeech 2023

This paper proposes MP-SENet, a novel Speech Enhancement Network which directly denoises Magnitude and Phase spectra in parallel. The proposed MP-SENet adopts a codec architecture in which the encoder and decoder are bridged by convolution-augmented transformers. The encoder aims to encode time-frequency representations from the input noisy magnitude and phase spectra. The decoder is composed of parallel magnitude mask decoder and phase decoder, directly recovering clean magnitude spectra and clean-wrapped phase spectra by incorporating learnable sigmoid activation and parallel phase estimation architecture, respectively. Multi-level losses defined on magnitude spectra, phase spectra, short-time complex spectra, and time-domain waveforms are used to train the MP-SENet model jointly. Experimental results show that our proposed MP-SENet achieves a PESQ of 3.50 on the public VoiceBank+DEMAND dataset and outperforms existing advanced speech enhancement methods., Comment: Accepted by Interspeech 2023

Modeling multi-party conversations (MPCs) with graph neural networks has been proven effective at capturing complicated and graphical information flows. However, existing methods rely heavily on the necessary addressee labels and can only be applied to an ideal setting where each utterance must be tagged with an addressee label. To study the scarcity of addressee labels which is a common issue in MPCs, we propose MADNet that maximizes addressee deduction expectation in heterogeneous graph neural networks for MPC generation. Given an MPC with a few addressee labels missing, existing methods fail to build a consecutively connected conversation graph, but only a few separate conversation fragments instead. To ensure message passing between these conversation fragments, four additional types of latent edges are designed to complete a fully-connected graph. Besides, to optimize the edge-type-dependent message passing for those utterances without addressee labels, an Expectation-Maximization-based method that iteratively generates silver addressee labels (E step), and optimizes the quality of generated responses (M step), is designed. Experimental results on two Ubuntu IRC channel benchmarks show that MADNet outperforms various baseline models on the task of MPC generation, especially under the more common and challenging setting where part of addressee labels are missing., Comment: Accepted by EMNLP 2023. arXiv admin note: text overlap with arXiv:2203.08500

Zero-shot cross-lingual information extraction(IE) aims at constructing an IE model for some low-resource target languages, given annotations exclusively in some rich-resource languages. Recent studies based on language-universal features have shown their effectiveness and are attracting increasing attention. However, prior work has neither explored the potential of establishing interactions between language-universal features and contextual representations nor incorporated features that can effectively model constituent span attributes and relationships between multiple spans. In this study, a syntax-augmented hierarchical interactive encoder (SHINE) is proposed to transfer cross-lingual IE knowledge. The proposed encoder is capable of interactively capturing complementary information between features and contextual information, to derive language-agnostic representations for various IE tasks. Concretely, a multi-level interaction network is designed to hierarchically interact the complementary information to strengthen domain adaptability. Besides, in addition to the well-studied syntax features of part-of-speech and dependency relation, a new syntax feature of constituency structure is introduced to model the constituent span information which is crucial for IE. Experiments across seven languages on three IE tasks and four benchmarks verify the effectiveness and generalization ability of the proposed method., Comment: 15pages

Diffusion models have emerged as the new state-of-the-art family of deep generative models, and their promising potentials for text generation have recently attracted increasing attention. Existing studies mostly adopt a single encoder architecture with partially noising processes for conditional text generation, but its degree of flexibility for conditional modeling is limited. In fact, the encoder-decoder architecture is naturally more flexible for its detachable encoder and decoder modules, which is extensible to multilingual and multimodal generation tasks for conditions and target texts. However, the encoding process of conditional texts lacks the understanding of target texts. To this end, a spiral interaction architecture for encoder-decoder text diffusion (DiffuSIA) is proposed. Concretely, the conditional information from encoder is designed to be captured by the diffusion decoder, while the target information from decoder is designed to be captured by the conditional encoder. These two types of information flow run through multilayer interaction spirally for deep fusion and understanding. DiffuSIA is evaluated on four text generation tasks, including paraphrase, text simplification, question generation, and open-domain dialogue generation. Experimental results show that DiffuSIA achieves competitive performance among previous methods on all four tasks, demonstrating the effectiveness and generalization ability of the proposed method., Comment: Work in Progress

Time-domain single-channel speech enhancement (SE) still remains challenging to extract the target speaker without any prior information on multi-talker conditions. It has been shown via auditory attention decoding that the brain activity of the listener contains the auditory information of the attended speaker. In this paper, we thus propose a novel time-domain brain-assisted SE network (BASEN) incorporating electroencephalography (EEG) signals recorded from the listener for extracting the target speaker from monaural speech mixtures. The proposed BASEN is based on the fully-convolutional time-domain audio separation network. In order to fully leverage the complementary information contained in the EEG signals, we further propose a convolutional multi-layer cross attention module to fuse the dual-branch features. Experimental results on a public dataset show that the proposed model outperforms the state-of-the-art method in several evaluation metrics. The reproducible code is available at https://github.com/jzhangU/Basen.git., Comment: Submitted to ISCA Interspeech 2023

Addressing the issues of who saying what to whom in multi-party conversations (MPCs) has recently attracted a lot of research attention. However, existing methods on MPC understanding typically embed interlocutors and utterances into sequential information flows, or utilize only the superficial of inherent graph structures in MPCs. To this end, we present a plug-and-play and lightweight method named graph-induced fine-tuning (GIFT) which can adapt various Transformer-based pre-trained language models (PLMs) for universal MPC understanding. In detail, the full and equivalent connections among utterances in regular Transformer ignore the sparse but distinctive dependency of an utterance on another in MPCs. To distinguish different relationships between utterances, four types of edges are designed to integrate graph-induced signals into attention mechanisms to refine PLMs originally designed for processing sequential texts. We evaluate GIFT by implementing it into three PLMs, and test the performance on three downstream tasks including addressee recognition, speaker identification and response selection. Experimental results show that GIFT can significantly improve the performance of three PLMs on three downstream tasks and two benchmarks with only 4 additional parameters per encoding layer, achieving new state-of-the-art performance on MPC understanding., Comment: Accepted by ACL 2023. arXiv admin note: substantial text overlap with arXiv:2106.01541

This paper presents a novel neural vocoder named APNet which reconstructs speech waveforms from acoustic features by predicting amplitude and phase spectra directly. The APNet vocoder is composed of an amplitude spectrum predictor (ASP) and a phase spectrum predictor (PSP). The ASP is a residual convolution network which predicts frame-level log amplitude spectra from acoustic features. The PSP also adopts a residual convolution network using acoustic features as input, then passes the output of this network through two parallel linear convolution layers respectively, and finally integrates into a phase calculation formula to estimate frame-level phase spectra. Finally, the outputs of ASP and PSP are combined to reconstruct speech waveforms by inverse short-time Fourier transform (ISTFT). All operations of the ASP and PSP are performed at the frame level. We train the ASP and PSP jointly and define multilevel loss functions based on amplitude mean square error, phase anti-wrapping error, short-time spectral inconsistency error and time domain reconstruction error. Experimental results show that our proposed APNet vocoder achieves an approximately 8x faster inference speed than HiFi-GAN v1 on a CPU due to the all-frame-level operations, while its synthesized speech quality is comparable to HiFi-GAN v1. The synthesized speech quality of the APNet vocoder is also better than that of several equally efficient models. Ablation experiments also confirm that the proposed parallel phase estimation architecture is essential to phase modeling and the proposed loss functions are helpful for improving the synthesized speech quality., Comment: Accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing. Codes are available

Lip-to-Speech (Lip2Speech) synthesis, which predicts corresponding speech from talking face images, has witnessed significant progress with various models and training strategies in a series of independent studies. However, existing studies can not achieve voice control under zero-shot condition, because extra speaker embeddings need to be extracted from natural reference speech and are unavailable when only the silent video of an unseen speaker is given. In this paper, we propose a zero-shot personalized Lip2Speech synthesis method, in which face images control speaker identities. A variational autoencoder is adopted to disentangle the speaker identity and linguistic content representations, which enables speaker embeddings to control the voice characteristics of synthetic speech for unseen speakers. Furthermore, we propose associated cross-modal representation learning to promote the ability of face-based speaker embeddings (FSE) on voice control. Extensive experiments verify the effectiveness of the proposed method whose synthetic utterances are more natural and matching with the personality of input video than the compared methods. To our best knowledge, this paper makes the first attempt on zero-shot personalized Lip2Speech synthesis with a face image rather than reference audio to control voice characteristics., Comment: ICASSP 2023

This paper describes the system developed by the USTC-NELSLIP team for SemEval-2023 Task 2 Multilingual Complex Named Entity Recognition (MultiCoNER II). A method named Statistical Construction and Dual Adaptation of Gazetteer (SCDAG) is proposed for Multilingual Complex NER. The method first utilizes a statistics-based approach to construct a gazetteer. Secondly, the representations of gazetteer networks and language models are adapted by minimizing the KL divergence between them at both the sentence-level and entity-level. Finally, these two networks are then integrated for supervised named entity recognition (NER) training. The proposed method is applied to XLM-R with a gazetteer built from Wikidata, and shows great generalization ability across different tracks. Experimental results and detailed analysis verify the effectiveness of the proposed method. The official results show that our system ranked 1st on one track (Hindi) in this task., Comment: Winner system (USTC-NELSLIP) of SemEval 2023 MultiCoNER II shared task on Hindi track. arXiv admin note: substantial text overlap with arXiv:2203.03216