arXiv subjects

Wei Han

Publications and source records attributed to Wei Han.

At least 145 records · Page 8Linked to original sources

arXiv2021

Multi-trends Enhanced Dynamic Micro-video Recommendation

The explosively generated micro-videos on content sharing platforms call for recommender systems to permit personalized micro-video discovery with ease. Recent advances in micro-video recommendation have achieved remarkable performance in mining users' current preference based on historical behaviors. However, most of them neglect the dynamic and time-evolving nature of users' preference, and the prediction on future micro-videos with historically mined preference may deteriorate the effectiveness of recommender systems. In this paper, we propose the DMR framework to explicitly model dynamic multi-trends of users' current preference and make predictions based on both the history and future potential trends. We devise the DMR framework, which comprises: 1) the implicit user network module which identifies sequence fragments from other users with similar interests and extracts the sequence fragments that are chronologically behind the identified fragments; 2) the multi-trend routing module which assigns each extracted sequence fragment into a trend group and update the corresponding trend vector; 3) the history-future trend prediction module jointly uses the history preference vectors and future trend vectors to yield the final click-through-rate. We validate the effectiveness of DMR over multiple state-of-the-art micro-video recommenders on two publicly available real-world datasets. Relatively extensive analysis further demonstrate the superiority of modeling dynamic multi-trend for micro-video recommendation.

cs.IR↗

arXiv2021

Half-integer Shapiro Steps in Strong Ferromagnetic Josephson Junctions

We report the experimental observation of half-integer Shapiro steps in the strong ferromagnetic Josephson junction (Nb-NiFe-Nb) by investigating the current-phase relation under radiofrequency microwave excitation. The half-integer Shapiro steps are robust in a wide temperature range from T = 4 to 7 K. The half-integer Shapiro steps could be attributed to co-existence of 0- and pi-states in the strong ferromagnetic NiFe Josephson junctions with the spatial variation of the2 NiFe thickness. This scenario is also supported by the high-resolution transmission electron microscopy characterization of the Nb/NiFe/Nb junction.

cond-mat.supr-con↗

arXiv2021

Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis

In multimodal sentiment analysis (MSA), the performance of a model highly depends on the quality of synthesized embeddings. These embeddings are generated from the upstream process called multimodal fusion, which aims to extract and combine the input unimodal raw data to produce a richer multimodal representation. Previous work either back-propagates the task loss or manipulates the geometric property of feature spaces to produce favorable fusion results, which neglects the preservation of critical task-related information that flows from input to the fusion results. In this work, we propose a framework named MultiModal InfoMax (MMIM), which hierarchically maximizes the Mutual Information (MI) in unimodal input pairs (inter-modality) and between multimodal fusion result and unimodal input in order to maintain task-related information through multimodal fusion. The framework is jointly trained with the main task (MSA) to improve the performance of the downstream MSA task. To address the intractable issue of MI bounds, we further formulate a set of computationally simple parametric and non-parametric methods to approximate their truth value. Experimental results on the two widely used datasets demonstrate the efficacy of our approach. The implementation of this work is publicly available at https://github.com/declare-lab/Multimodal-Infomax.

cs.CL↗

arXiv2021

W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training

Motivated by the success of masked language modeling~(MLM) in pre-training natural language processing models, we propose w2v-BERT that explores MLM for self-supervised speech representation learning. w2v-BERT is a framework that combines contrastive learning and MLM, where the former trains the model to discretize input continuous speech signals into a finite set of discriminative speech tokens, and the latter trains the model to learn contextualized speech representations via solving a masked prediction task consuming the discretized tokens. In contrast to existing MLM-based speech pre-training frameworks such as HuBERT, which relies on an iterative re-clustering and re-training process, or vq-wav2vec, which concatenates two separately trained modules, w2v-BERT can be optimized in an end-to-end fashion by solving the two self-supervised tasks~(the contrastive task and MLM) simultaneously. Our experiments show that w2v-BERT achieves competitive results compared to current state-of-the-art pre-trained models on the LibriSpeech benchmarks when using the Libri-Light~60k corpus as the unsupervised data. In particular, when compared to published models such as conformer-based wav2vec~2.0 and HuBERT, our model shows~5\% to~10\% relative WER reduction on the test-clean and test-other subsets. When applied to the Google's Voice Search traffic dataset, w2v-BERT outperforms our internal conformer-based wav2vec~2.0 by more than~30\% relatively.

cs.LG↗

arXiv2021

Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis

Multimodal sentiment analysis aims to extract and integrate semantic information collected from multiple modalities to recognize the expressed emotions and sentiment in multimodal data. This research area's major concern lies in developing an extraordinary fusion scheme that can extract and integrate key information from various modalities. However, one issue that may restrict previous work to achieve a higher level is the lack of proper modeling for the dynamics of the competition between the independence and relevance among modalities, which could deteriorate fusion outcomes by causing the collapse of modality-specific feature space or introducing extra noise. To mitigate this, we propose the Bi-Bimodal Fusion Network (BBFN), a novel end-to-end network that performs fusion (relevance increment) and separation (difference increment) on pairwise modality representations. The two parts are trained simultaneously such that the combat between them is simulated. The model takes two bimodal pairs as input due to the known information imbalance among modalities. In addition, we leverage a gated control mechanism in the Transformer architecture to further improve the final output. Experimental results on three datasets (CMU-MOSI, CMU-MOSEI, and UR-FUNNY) verifies that our model significantly outperforms the SOTA. The implementation of this work is available at https://github.com/declare-lab/multimodal-deep-learning.

cs.AI↗

arXiv2021

Supervised Contrastive Learning for Accented Speech Recognition

Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents. In this paper, we study the supervised contrastive learning framework for accented speech recognition. To build different views (similar "positive" data samples) for contrastive learning, three data augmentation techniques including noise injection, spectrogram augmentation and TTS-same-sentence generation are further investigated. From the experiments on the Common Voice dataset, we have shown that contrastive learning helps to build data-augmentation invariant and pronunciation invariant representations, which significantly outperforms traditional joint training methods in both zero-shot and full-shot settings. Experiments show that contrastive learning can improve accuracy by 3.66% (zero-shot) and 3.78% (full-shot) on average, comparing to the joint training method.

cs.SD↗

arXiv2021

Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks

Dialogue relation extraction (DRE) aims to detect the relation between two entities mentioned in a multi-party dialogue. It plays an important role in constructing knowledge graphs from conversational data increasingly abundant on the internet and facilitating intelligent dialogue system development. The prior methods of DRE do not meaningfully leverage speaker information-they just prepend the utterances with the respective speaker names. Thus, they fail to model the crucial inter-speaker relations that may give additional context to relevant argument entities through pronouns and triggers. We, however, present a graph attention network-based method for DRE where a graph, that contains meaningfully connected speaker, entity, entity-type, and utterance nodes, is constructed. This graph is fed to a graph attention network for context propagation among relevant nodes, which effectively captures the dialogue context. We empirically show that this graph-based approach quite effectively captures the relations between different entity pairs in a dialogue as it outperforms the state-of-the-art approaches by a significant margin on the benchmark dataset DialogRE. Our code is released at: https://github.com/declare-lab/dialog-HGAT

cs.CL↗

arXiv2021

Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models

Streaming end-to-end automatic speech recognition (ASR) systems are widely used in everyday applications that require transcribing speech to text in real-time. Their minimal latency makes them suitable for such tasks. Unlike their non-streaming counterparts, streaming models are constrained to be causal with no future context and suffer from higher word error rates (WER). To improve streaming models, a recent study [1] proposed to distill a non-streaming teacher model on unsupervised utterances, and then train a streaming student using the teachers' predictions. However, the performance gap between teacher and student WERs remains high. In this paper, we aim to close this gap by using a diversified set of non-streaming teacher models and combining them using Recognizer Output Voting Error Reduction (ROVER). In particular, we show that, despite being weaker than RNN-T models, CTC models are remarkable teachers. Further, by fusing RNN-T and CTC models together, we build the strongest teachers. The resulting student models drastically improve upon streaming models of previous work [1]: the WER decreases by 41% on Spanish, 27% on Portuguese, and 13% on French.

cs.CL↗

arXiv2021

Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models

Although end-to-end automatic speech recognition (e2e ASR) models are widely deployed in many applications, there have been very few studies to understand models' robustness against adversarial perturbations. In this paper, we explore whether a targeted universal perturbation vector exists for e2e ASR models. Our goal is to find perturbations that can mislead the models to predict the given targeted transcript such as "thank you" or empty string on any input utterance. We study two different attacks, namely additive and prepending perturbations, and their performances on the state-of-the-art LAS, CTC and RNN-T models. We find that LAS is the most vulnerable to perturbations among the three models. RNN-T is more robust against additive perturbations, especially on long utterances. And CTC is robust against both additive and prepending perturbations. To attack RNN-T, we find prepending perturbation is more effective than the additive perturbation, and can mislead the models to predict the same short target on utterances of arbitrary length.

eess.AS↗

arXiv2021

Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with no future context, compared to their non-streaming counterparts. Consequently, streaming models usually perform worse than non-streaming models. We propose a novel and effective learning method by leveraging a non-streaming ASR model as a teacher to generate transcripts on an arbitrarily large data set, which is then used to distill knowledge into streaming ASR models. This way, we scale the training of streaming models to up to 3 million hours of YouTube audio. Experiments show that our approach can significantly reduce the word error rate (WER) of RNNT models not only on LibriSpeech but also on YouTube data in four languages. For example, in French, we are able to reduce the WER by 16.4% relatively to a baseline streaming model by leveraging a non-streaming teacher model trained on the same amount of labeled data as the baseline.

cs.SD↗

arXiv2021

A Better and Faster End-to-End Model for Streaming ASR

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by word error rate (WER)) and endpointer latency [2]. However, the model still tends to delay the predictions towards the end and thus has much higher partial latency compared to a conventional ASR model. To address this issue, we look at encouraging the E2E model to emit words early, through an algorithm called FastEmit [3]. Naturally, improving on latency results in a quality degradation. To address this, we explore replacing the LSTM layers in the encoder of our E2E model with Conformer layers [4], which has shown good improvements for ASR. Secondly, we also explore running a 2nd-pass beam search to improve quality. In order to ensure the 2nd-pass completes quickly, we explore non-causal Conformer layers that feed into the same 1st-pass RNN-T decoder, an algorithm called Cascaded Encoders [5]. Overall, we find that the Conformer RNN-T with Cascaded Encoders offers a better quality and latency tradeoff for streaming ASR.

eess.AS↗

arXiv2021

FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measured by word error rate (WER), is highly challenging. Existing approaches including Early and Late Penalties and Constrained Alignments penalize emission delay by manipulating per-token or per-frame probability prediction in sequence transducer models. While being successful in reducing delay, these approaches suffer from significant accuracy regression and also require additional word alignment information from an existing model. In this work, we propose a sequence-level emission regularization method, named FastEmit, that applies latency regularization directly on per-sequence probability in training transducer models, and does not require any alignment. We demonstrate that FastEmit is more suitable to the sequence-level optimization of transducer models for streaming ASR by applying it on various end-to-end streaming ASR networks including RNN-Transducer, Transformer-Transducer, ConvNet-Transducer and Conformer-Transducer. We achieve 150-300 ms latency reduction with significantly better accuracy over previous techniques on a Voice Search test set. FastEmit also improves streaming ASR accuracy from 4.4%/8.9% to 3.1%/7.5% WER, meanwhile reduces 90th percentile latency from 210 ms to only 30 ms on LibriSpeech.

eess.AS↗

arXiv2021

Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this work, we propose a unified framework, Dual-mode ASR, to train a single end-to-end ASR model with shared weights for both streaming and full-context speech recognition. We show that the latency and accuracy of streaming ASR significantly benefit from weight sharing and joint training of full-context ASR, especially with inplace knowledge distillation during the training. The Dual-mode ASR framework can be applied to recent state-of-the-art convolution-based and transformer-based ASR networks. We present extensive experiments with two state-of-the-art ASR networks, ContextNet and Conformer, on two datasets, a widely used public dataset LibriSpeech and a large-scale dataset MultiDomain. Experiments and ablation studies demonstrate that Dual-mode ASR not only simplifies the workflow of training and deploying streaming and full-context ASR models, but also significantly improves both emission latency and recognition accuracy of streaming ASR. With Dual-mode ASR, we achieve new state-of-the-art streaming ASR results on both LibriSpeech and MultiDomain in terms of accuracy and latency.

cs.CL↗

arXiv2020

RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions

In recent years, all-neural end-to-end approaches have obtained state-of-the-art results on several challenging automatic speech recognition (ASR) tasks. However, most existing works focus on building ASR models where train and test data are drawn from the same domain. This results in poor generalization characteristics on mismatched-domains: e.g., end-to-end models trained on short segments perform poorly when evaluated on longer utterances. In this work, we analyze the generalization properties of streaming and non-streaming recurrent neural network transducer (RNN-T) based end-to-end models in order to identify model components that negatively affect generalization performance. We propose two solutions: combining multiple regularization techniques during training, and using dynamic overlapping inference. On a long-form YouTube test set, when the nonstreaming RNN-T model is trained with shorter segments of data, the proposed combination improves word error rate (WER) from 22.3% to 14.8%; when the streaming RNN-T model trained on short Search queries, the proposed techniques improve WER on the YouTube set from 67.0% to 25.3%. Finally, when trained on Librispeech, we find that dynamic overlapping inference improves WER on YouTube from 99.8% to 33.0%.

eess.AS↗

arXiv2020

Superconductor-metal quantum transition at the EuO-KTaO3 interface

Superconductivity has been one of the most fascinating quantum states of matter for over several decades. Among the superconducting materials, LaAlO3/SrTiO3 interface is of particularly interest since superconductivity exists between two insulating materials, which provides it with various unique applications compared with bulk superconductors and makes it a suitable platform to study the quantum Hall effect, charge density wave, superconductivity and magnetism in one device. Therefore, a lot of efforts have been made to search new superconducting oxide interface states with higher superconducting critical temperature (TC). Recently, a superconducting state with TC ~ 2 K has been found at the interface between a ferromagnetic insulator EuO and a band insulator (111)-KTaO3. Here, we report the experimental investigation of the superconductor-metal quantum phase transition of the EuO/KTaO3 interface. Around the transition, a divergence of the dynamical critical exponent is observed, which supports the quantum Griffiths singularity in the EuO/KTaO3 interface. The quantum Griffiths singularity could be attributed to large rare superconducting regions and quenched disorders at the interface. Our results could pave the way for studying the exotic superconducting properties at the EuO/KTaO3 interface.

cond-mat.supr-con↗

arXiv2020

Facet-dependent magnon-polarons in epitaxial ferrimagnetic Fe3O4 thin films

Magnon-polarons are coherently mixed quasiparticles that originate from the strong magnetoelastic coupling of lattice vibrations and spin waves in magnetic-ordered materials. Recently, magnon-polarons have attracted a lot of attention since they provide a powerful tool to manipulate magnons, which is essential for magnon-based spintronic devices. In this work, we report the experimental observation of facet-dependent magnon-polarons in epitaxial ferrimagnetic Fe3O4 thin films via spin Seebeck effect measurement. The critical magnetic fields for the magnon-polarons in the (110)- and (100)-oriented Fe3O4 films are 1.5 T and 1.8 T, respectively, which arises from the different phonon velocities along the [110] and [100] directions. As the temperature decreases, the magnon-polarons-enhanced spin Seebeck voltage decreases in both (110)- and (100)-oriented Fe3O4 films, which could be attributed to the enhanced magnon-polarons scattering at elevated temperatures. This work demonstrates the crystal structure engineering in epitaxial magnetic films as a promising route to manipulate the magnon-polarons for future magnon spintronic applications.

cond-mat.mtrl-sci↗

arXiv2020

Improved Noisy Student Training for Automatic Speech Recognition

Recently, a semi-supervised learning method known as "noisy student training" has been shown to improve image classification performance of deep networks significantly. Noisy student training is an iterative self-training method that leverages augmentation to improve network performance. In this work, we adapt and improve noisy student training for automatic speech recognition, employing (adaptive) SpecAugment as the augmentation method. We find effective methods to filter, balance and augment the data generated in between self-training iterations. By doing so, we are able to obtain word error rates (WERs) 4.2%/8.6% on the clean/noisy LibriSpeech test sets by only using the clean 100h subset of LibriSpeech as the supervised set and the rest (860h) as the unlabeled set. Furthermore, we are able to achieve WERs 1.7%/3.4% on the clean/noisy LibriSpeech test sets by using the unlab-60k subset of LibriLight as the unlabeled set for LibriSpeech 960h. We are thus able to improve upon the previous state-of-the-art clean/noisy test WERs achieved on LibriSpeech 100h (4.74%/12.20%) and LibriSpeech (1.9%/4.1%).

eess.AS↗

arXiv2020

Answer-checking in Context: A Multi-modal FullyAttention Network for Visual Question Answering

Visual Question Answering (VQA) is challenging due to the complex cross-modal relations. It has received extensive attention from the research community. From the human perspective, to answer a visual question, one needs to read the question and then refer to the image to generate an answer. This answer will then be checked against the question and image again for the final confirmation. In this paper, we mimic this process and propose a fully attention based VQA architecture. Moreover, an answer-checking module is proposed to perform a unified attention on the jointly answer, question and image representation to update the answer. This mimics the human answer checking process to consider the answer in the context. With answer-checking modules and transferred BERT layers, our model achieves the state-of-the-art accuracy 71.57\% using fewer parameters on VQA-v2.0 test-standard split.

cs.CV↗