arXiv subjects

Ao Zhang

Publications and source records attributed to Ao Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2023

Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network

Contextual information plays a crucial role in speech recognition technologies and incorporating it into the end-to-end speech recognition models has drawn immense interest recently. However, previous deep bias methods lacked explicit supervision for bias tasks. In this study, we introduce a contextual phrase prediction network for an attention-based deep bias method. This network predicts context phrases in utterances using contextual embeddings and calculates bias loss to assist in the training of the contextualized model. Our method achieved a significant word error rate (WER) reduction across various end-to-end speech recognition models. Experiments on the LibriSpeech corpus show that our proposed model obtains a 12.1% relative WER improvement over the baseline model, and the WER of the context phrases decreases relatively by 40.5%. Moreover, by applying a context phrase filtering strategy, we also effectively eliminate the WER degradation when using a larger biasing list.

eess.AS↗

arXiv2023

Visually Grounded Commonsense Knowledge Acquisition

Large-scale commonsense knowledge bases empower a broad range of AI applications, where the automatic extraction of commonsense knowledge (CKE) is a fundamental and challenging problem. CKE from text is known for suffering from the inherent sparsity and reporting bias of commonsense in text. Visual perception, on the other hand, contains rich commonsense knowledge about real-world entities, e.g., (person, can_hold, bottle), which can serve as promising sources for acquiring grounded commonsense knowledge. In this work, we present CLEVER, which formulates CKE as a distantly supervised multi-instance learning problem, where models learn to summarize commonsense relations from a bag of images about an entity pair without any human annotation on image instances. To address the problem, CLEVER leverages vision-language pre-training models for deep understanding of each image in the bag, and selects informative instances from the bag to summarize commonsense entity relations via a novel contrastive attention mechanism. Comprehensive experimental results in held-out and human evaluation show that CLEVER can extract commonsense knowledge in promising quality, outperforming pre-trained language model-based methods by 3.9 AUC and 6.4 mAUC points. The predicted commonsense scores show strong correlation with human judgment with a 0.78 Spearman coefficient. Moreover, the extracted commonsense can also be grounded into images with reasonable interpretability. The data and codes can be obtained at https://github.com/thunlp/CLEVER.

cs.CV↗

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

The NPU-ASLP System for Audio-Visual Speech Recognition in MISP 2022 Challenge

This paper describes our NPU-ASLP system for the Audio-Visual Diarization and Recognition (AVDR) task in the Multi-modal Information based Speech Processing (MISP) 2022 Challenge. Specifically, the weighted prediction error (WPE) and guided source separation (GSS) techniques are used to reduce reverberation and generate clean signals for each single speaker first. Then, we explore the effectiveness of Branchformer and E-Branchformer based ASR systems. To better make use of the visual modality, a cross-attention based multi-modal fusion module is proposed, which explicitly learns the contextual relationship between different modalities. Experiments show that our system achieves a concatenated minimum-permutation character error rate (cpCER) of 28.13\% and 31.21\% on the Dev and Eval set, and obtains second place in the challenge.

eess.AS↗

arXiv2022

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models

Vision-language pre-training (VLP) has shown impressive performance on a wide range of cross-modal tasks, where VLP models without reliance on object detectors are becoming the mainstream due to their superior computation efficiency and competitive performance. However, the removal of object detectors also deprives the capability of VLP models in explicit object modeling, which is essential to various position-sensitive vision-language (VL) tasks, such as referring expression comprehension and visual commonsense reasoning. To address the challenge, we introduce PEVL that enhances the pre-training and prompt tuning of VLP models with explicit object position modeling. Specifically, PEVL reformulates discretized object positions and language in a unified language modeling framework, which facilitates explicit VL alignment during pre-training, and also enables flexible prompt tuning for various downstream tasks. We show that PEVL enables state-of-the-art performance of detector-free VLP models on position-sensitive tasks such as referring expression comprehension and phrase grounding, and also improves the performance on position-insensitive tasks with grounded inputs. We make the data and code for this paper publicly available at https://github.com/thunlp/PEVL.

cs.CV↗

arXiv2022

Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing

Data augmentation has attracted a lot of research attention in the deep learning era for its ability in alleviating data sparseness. The lack of labeled data for unseen evaluation databases is exactly the major challenge for cross-domain text-to-SQL parsing. Previous works either require human intervention to guarantee the quality of generated data, or fail to handle complex SQL queries. This paper presents a simple yet effective data augmentation framework. First, given a database, we automatically produce a large number of SQL queries based on an abstract syntax tree grammar. For better distribution matching, we require that at least 80% of SQL patterns in the training data are covered by generated queries. Second, we propose a hierarchical SQL-to-question generation model to obtain high-quality natural language questions, which is the major contribution of this work. Finally, we design a simple sampling strategy that can greatly improve training efficiency given large amounts of generated data. Experiments on three cross-domain datasets, i.e., WikiSQL and Spider in English, and DuSQL in Chinese, show that our proposed data augmentation framework can consistently improve performance over strong baselines, and the hierarchical generation component is the key for the improvement.

cs.CL↗

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

Chiral Dirac-like fermion in spin-orbit-free antiferromagnetic semimetals

Dirac semimetal is a phase of matter, whose elementary excitation is described by the relativistic Dirac equation. In the limit of zero mass, its parity-time symmetry enforces the Dirac fermion in the momentum space, which is composed of two Weyl fermions with opposite chirality, to be non-chiral. Inspired by the flavor symmetry in particle physics, we theoretically propose a massless Dirac-like equation yet linking two Weyl fields with the identical chirality by assuming SU(2) isospin symmetry, independent of the space-time rotation exchanging the two fields. Dramatically, such symmetry is hidden in certain solid-state spin-1/2 systems with negligible spin-orbit coupling, where the spin degree of freedom is decoupled with the lattice. Therefore, the existence of the corresponding quasiparticle, dubbed as flavor Weyl fermion, cannot be explained by the conventional (magnetic) space group framework. The four-fold degenerate flavor Weyl fermion manifests linear dispersion and a Chern number of 2, leading to a robust network of topologically protected Fermi arcs throughout the Brillouin zone. For material realization, we show that the transition-metal chalcogenide CoNb3S6 with experimentally confirmed collinear antiferromagnetic order is ideal for flavor Weyl semimetal under the approximation of vanishing spin-orbit coupling. Our work reveals a counterpart of the flavor symmetry in magnetic electronic systems, leading to further possibilities of emergent phenomena in quantum materials.

cond-mat.mtrl-sci↗

arXiv2022

Fine-Grained Scene Graph Generation with Data Transfer

Scene graph generation (SGG) is designed to extract (subject, predicate, object) triplets in images. Recent works have made a steady progress on SGG, and provide useful tools for high-level vision and language understanding. However, due to the data distribution problems including long-tail distribution and semantic ambiguity, the predictions of current SGG models tend to collapse to several frequent but uninformative predicates (e.g., on, at), which limits practical application of these models in downstream tasks. To deal with the problems above, we propose a novel Internal and External Data Transfer (IETrans) method, which can be applied in a plug-and-play fashion and expanded to large SGG with 1,807 predicate classes. Our IETrans tries to relieve the data distribution problem by automatically creating an enhanced dataset that provides more sufficient and coherent annotations for all predicates. By training on the enhanced dataset, a Neural Motif model doubles the macro performance while maintaining competitive micro performance. The code and data are publicly available at https://github.com/waxnkw/IETrans-SGG.pytorch.

cs.CV↗

arXiv2022

Minimizing Sequential Confusion Error in Speech Command Recognition

Speech command recognition (SCR) has been commonly used on resource constrained devices to achieve hands-free user experience. However, in real applications, confusion among commands with similar pronunciations often happens due to the limited capacity of small models deployed on edge devices, which drastically affects the user experience. In this paper, inspired by the advances of discriminative training in speech recognition, we propose a novel minimize sequential confusion error (MSCE) training criterion particularly for SCR, aiming to alleviate the command confusion problem. Specifically, we aim to improve the ability of discriminating the target command from other commands on the basis of MCE discriminative criteria. We define the likelihood of different commands through connectionist temporal classification (CTC). During training, we propose several strategies to use prior knowledge creating a confusing sequence set for similar-sounding command instead of creating the whole non-target command set, which can better save the training resources and effectively reduce command confusion errors. Specifically, we design and compare three different strategies for confusing set construction. By using our proposed method, we can relatively reduce the False Reject Rate~(FRR) by 33.7% at 0.01 False Alarm Rate~(FAR) and confusion errors by 18.28% on our collected speech command set.

cs.SD↗

arXiv2022

Prompt Tuning for Discriminative Pre-trained Language Models

Recent works have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing (NLP) tasks. However, to the best of our knowledge, existing works focus on prompt-tuning generative PLMs that are pre-trained to generate target tokens, such as BERT. It is still unknown whether and how discriminative PLMs, e.g., ELECTRA, can be effectively prompt-tuned. In this work, we present DPT, the first prompt tuning framework for discriminative PLMs, which reformulates NLP tasks into a discriminative language modeling problem. Comprehensive experiments on text classification and question answering show that, compared with vanilla fine-tuning, DPT achieves significantly higher performance, and also prevents the unstable problem in tuning large PLMs in both full-set and low-resource settings. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/DPT.

cs.CL↗

arXiv2022

CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models

Pre-Trained Vision-Language Models (VL-PTMs) have shown promising capabilities in grounding natural language in image data, facilitating a broad variety of cross-modal tasks. However, we note that there exists a significant gap between the objective forms of model pre-training and fine-tuning, resulting in a need for large amounts of labeled data to stimulate the visual grounding capability of VL-PTMs for downstream tasks. To address the challenge, we present Cross-modal Prompt Tuning (CPT, alternatively, Colorful Prompt Tuning), a novel paradigm for tuning VL-PTMs, which reformulates visual grounding into a fill-in-the-blank problem with color-based co-referential markers in image and text, maximally mitigating the gap. In this way, CPT enables strong few-shot and even zero-shot visual grounding capabilities of VL-PTMs. Comprehensive experimental results show that the prompt-tuned VL-PTMs outperform their fine-tuned counterparts by a large margin (e.g., 17.3% absolute accuracy improvement, and 73.8% relative standard deviation reduction on average with one shot in RefCOCO evaluation). We make the data and code for this paper publicly available at https://github.com/thunlp/CPT.

cs.CV↗

arXiv2021

Electrically switchable valley polarization, spin/valley filter, and valve effects in transition-metal dichalcogenide monolayers interfaced with two-dimensional ferromagnetic semiconductors

Electron valleys in transition-metal dichalcogenide monolayers drive novel physics and allow designing multifunctional architectures for applications. We propose to manipulate the electron valleys in these systems for spin/valley filter and valve devices through band engineering. Instead of the magnetic proximity effect that has been extensively used in previous studies, in our strategy, the electron valleys are directly coupled to the spin-polarized states of the two-dimensional ferromagnets. We find that this coupling results in a valley-selective gap opening due to the spin-momentum locking in the transition-metal dichalcogenide monolayers. This physics gives rise to a variety of unexpected electronic properties and phenomena including halfmetallicity, electrically switchable valley polarization, spin/valley filter and valve effects in the transition-metal dichalcogenide monolayers. We further demonstrate our idea in MoTe$_2$/CoCl$_2$ and CoCl$_2$/MoTe$_2$/CoCl$_2$ van der Waals heterojunctions based on first-principles calculations. Thus, our study provides a way of engineering the electron valleys in transition-metal dichalcogenide monolayers for new-concept devices.

cond-mat.mes-hall↗

arXiv2021

Bohmian Trajectories of the Time-oscillating Schrödinger Equations

Bohmian mechanics is a non-relativistic quantum theory based on a particle approach. In this paper we study the Schrödinger equation with rapidly oscillating potential and the associated Bohmian trajectory. We prove that the corresponding Bohmian trajectory converges locally in measure, and the limit coincides with the Bohmian trajectory for the effective Schrödinger equation on a finite time interval. This is beneficial for the efficient simulation of the Bohmian trajectories in oscillating potential fields.

math-ph↗

arXiv2021

Kantorovich-Rubinstein Distance and Approximation for Non-local Fokker-Planck Equations

This work is devoted to studying complex dynamical systems under non-Gaussian fluctuations. We first estimate the Kantorovich-Rubinstein distance for solutions of non-local Fokker-Planck equations associated with stochastic differential equations with non-Gaussian Levy noise. This is then applied to establish weak convergence of the corresponding probability distributions. Furthermore, this leads to smooth approximation for non-local Fokker-Planck equations, as illustrated in an example.

math.PR↗

arXiv2021

Visual Distant Supervision for Scene Graph Generation

Scene graph generation aims to identify objects and their relations in images, providing structured image representations that can facilitate numerous applications in computer vision. However, scene graph models usually require supervised learning on large quantities of labeled data with intensive human annotation. In this work, we propose visual distant supervision, a novel paradigm of visual relation learning, which can train scene graph models without any human-labeled data. The intuition is that by aligning commonsense knowledge bases and images, we can automatically create large-scale labeled data to provide distant supervision for visual relation learning. To alleviate the noise in distantly labeled data, we further propose a framework that iteratively estimates the probabilistic relation labels and eliminates the noisy ones. Comprehensive experimental results show that our distantly supervised model outperforms strong weakly supervised and semi-supervised baselines. By further incorporating human-labeled data in a semi-supervised fashion, our model outperforms state-of-the-art fully supervised models by a large margin (e.g., 8.3 micro- and 7.8 macro-recall@50 improvements for predicate classification in Visual Genome evaluation). We make the data and code for this paper publicly available at https://github.com/thunlp/VisualDS.

cs.CV↗

arXiv2021

Pre-Trained Models: Past, Present and Future

Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI). Owing to sophisticated pre-training objectives and huge model parameters, large-scale PTMs can effectively capture knowledge from massive labeled and unlabeled data. By storing knowledge into huge parameters and fine-tuning on specific tasks, the rich knowledge implicitly encoded in huge parameters can benefit a variety of downstream tasks, which has been extensively demonstrated via experimental verification and empirical analysis. It is now the consensus of the AI community to adopt PTMs as backbone for downstream tasks rather than learning models from scratch. In this paper, we take a deep look into the history of pre-training, especially its special relation with transfer learning and self-supervised learning, to reveal the crucial position of PTMs in the AI development spectrum. Further, we comprehensively review the latest breakthroughs of PTMs. These breakthroughs are driven by the surge of computational power and the increasing availability of data, towards four important directions: designing effective architectures, utilizing rich contexts, improving computational efficiency, and conducting interpretation and theoretical analysis. Finally, we discuss a series of open problems and research directions of PTMs, and hope our view can inspire and advance the future study of PTMs.

cs.AI↗

arXiv2021

RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users

Object detection using automotive radars has not been explored with deep learning models in comparison to the camera based approaches. This can be attributed to the lack of public radar datasets. In this paper, we collect a novel radar dataset that contains radar data in the form of Range-Azimuth-Doppler tensors along with the bounding boxes on the tensor for dynamic road users, category labels, and 2D bounding boxes on the Cartesian Bird-Eye-View range map. To build the dataset, we propose an instance-wise auto-annotation method. Furthermore, a novel Range-Azimuth-Doppler based multi-class object detection deep learning model is proposed. The algorithm is a one-stage anchor-based detector that generates both 3D bounding boxes and 2D bounding boxes on Range-Azimuth-Doppler and Cartesian domains, respectively. Our proposed algorithm achieves 56.3% AP with IOU of 0.3 on 3D bounding box predictions, and 51.6% with IOU of 0.5 on 2D bounding box prediction. Our dataset and the code can be found at https://github.com/ZhangAoCanada/RADDet.git.

cs.CV↗