Search

Deep learning has achieved great success in the past few years. However, the performance of deep learning is likely to impede in face of non-IID situations. Domain generalization (DG) enables a model to generalize to an unseen test distribution, i.e., to learn domain-invariant representations. In this paper, we argue that domain-invariant features should be originating from both internal and mutual sides. Internal invariance means that the features can be learned with a single domain and the features capture intrinsic semantics of data, i.e., the property within a domain, which is agnostic to other domains. Mutual invariance means that the features can be learned with multiple domains (cross-domain) and the features contain common information, i.e., the transferable features w.r.t. other domains. We then propose DIFEX for Domain-Invariant Feature EXploration. DIFEX employs a knowledge distillation framework to capture the high-level Fourier phase as the internally-invariant features and learn cross-domain correlation alignment as the mutually-invariant features. We further design an exploration loss to increase the feature diversity for better generalization. Extensive experiments on both time-series and visual benchmarks demonstrate that the proposed DIFEX achieves state-of-the-art performance., Comment: Accepted by Transactions on Machine Learning Research (TMLR) 2022; 20 pages; code: https://github.com/jindongwang/transferlearning/tree/master/code/DeepDG

Human activity recognition requires the efforts to build a generalizable model using the training datasets with the hope to achieve good performance in test datasets. However, in real applications, the training and testing datasets may have totally different distributions due to various reasons such as different body shapes, acting styles, and habits, damaging the model's generalization performance. While such a distribution gap can be reduced by existing domain adaptation approaches, they typically assume that the test data can be accessed in the training stage, which is not realistic. In this paper, we consider a more practical and challenging scenario: domain-generalized activity recognition (DGAR) where the test dataset \emph{cannot} be accessed during training. To this end, we propose \emph{Adaptive Feature Fusion for Activity Recognition~(AFFAR)}, a domain generalization approach that learns to fuse the domain-invariant and domain-specific representations to improve the model's generalization performance. AFFAR takes the best of both worlds where domain-invariant representations enhance the transferability across domains and domain-specific representations leverage the model discrimination power from each domain. Extensive experiments on three public HAR datasets show its effectiveness. Furthermore, we apply AFFAR to a real application, i.e., the diagnosis of Children's Attention Deficit Hyperactivity Disorder~(ADHD), which also demonstrates the superiority of our approach., Comment: Accepted by ACM Transactions on Intelligent Systems and Technology (TIST) 2022; Code: https://github.com/jindongwang/transferlearning/tree/master/code/DeepDG

The wide spread of fake news is increasingly threatening both individuals and society. Great efforts have been made for automatic fake news detection on a single domain (e.g., politics). However, correlations exist commonly across multiple news domains, and thus it is promising to simultaneously detect fake news of multiple domains. Based on our analysis, we pose two challenges in multi-domain fake news detection: 1) domain shift, caused by the discrepancy among domains in terms of words, emotions, styles, etc. 2) domain labeling incompleteness, stemming from the real-world categorization that only outputs one single domain label, regardless of topic diversity of a news piece. In this paper, we propose a Memory-guided Multi-view Multi-domain Fake News Detection Framework (M$^3$FEND) to address these two challenges. We model news pieces from a multi-view perspective, including semantics, emotion, and style. Specifically, we propose a Domain Memory Bank to enrich domain information which could discover potential domain labels based on seen news pieces and model domain characteristics. Then, with enriched domain information as input, a Domain Adapter could adaptively aggregate discriminative information from multiple views for news in various domains. Extensive offline experiments on English and Chinese datasets demonstrate the effectiveness of M$^3$FEND, and online tests verify its superiority in practice. Our code is available at https://github.com/ICTMCG/M3FEND., Comment: Accepted by IEEE Transactions on Knowledge and Data Engineering (TKDE)

The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domain usually lacks labeled data, and domain shifts exist at acoustic and linguistic levels, it is challenging to perform unsupervised domain adaptation (UDA) for ASR. Previous work has shown that self-supervised learning (SSL) or pseudo-labeling (PL) is effective in UDA by exploiting the self-supervisions of unlabeled data. However, these self-supervisions also face performance degradation in mismatched domain distributions, which previous work fails to address. This work presents a systematic UDA framework to fully utilize the unlabeled data with self-supervision in the pre-training and fine-tuning paradigm. On the one hand, we apply continued pre-training and data replay techniques to mitigate the domain mismatch of the SSL pre-trained model. On the other hand, we propose a domain-adaptive fine-tuning approach based on the PL technique with three unique modifications: Firstly, we design a dual-branch PL method to decrease the sensitivity to the erroneous pseudo-labels; Secondly, we devise an uncertainty-aware confidence filtering strategy to improve pseudo-label correctness; Thirdly, we introduce a two-step PL approach to incorporate target domain linguistic knowledge, thus generating more accurate target domain pseudo-labels. Experimental results on various cross-domain scenarios demonstrate that the proposed approach effectively boosts the cross-domain performance and significantly outperforms previous approaches., Comment: Accepted by IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), 2023

Automatic speech recognition (ASR) with federated learning (FL) makes it possible to leverage data from multiple clients without compromising privacy. The quality of FL-based ASR could be measured by recognition performance, communication and computation costs. When data among different clients are not independently and identically distributed (non-IID), the performance could degrade significantly. In this work, we tackle the non-IID issue in FL-based ASR with personalized FL, which learns personalized models for each client. Concretely, we propose two types of personalized FL approaches for ASR. Firstly, we adapt the personalization layer based FL for ASR, which keeps some layers locally to learn personalization models. Secondly, to reduce the communication and computation costs, we propose decoupled federated learning (DecoupleFL). On one hand, DecoupleFL moves the computation burden to the server, thus decreasing the computation on clients. On the other hand, DecoupleFL communicates secure high-level features instead of model parameters, thus reducing communication cost when models are large. Experiments demonstrate two proposed personalized FL-based ASR approaches could reduce WER by 2.3% - 3.4% compared with FedAvg. Among them, DecoupleFL has only 11.4% communication and 75% computation cost compared with FedAvg, which is also significantly less than the personalization layer based FL., Comment: Accepted by Interspeech 2022

Federated learning has attracted increasing attention to building models without accessing the raw user data, especially in healthcare. In real applications, different federations can seldom work together due to possible reasons such as data heterogeneity and distrust/inexistence of the central server. In this paper, we propose a novel framework called MetaFed to facilitate trustworthy FL between different federations. MetaFed obtains a personalized model for each federation without a central server via the proposed Cyclic Knowledge Distillation. Specifically, MetaFed treats each federation as a meta distribution and aggregates knowledge of each federation in a cyclic manner. The training is split into two parts: common knowledge accumulation and personalization. Comprehensive experiments on three benchmarks demonstrate that MetaFed without a server achieves better accuracy compared to state-of-the-art methods (e.g., 10%+ accuracy improvement compared to the baseline for PAMAP2) with fewer communication costs., Comment: Accepted by IEEE Trans. on Neural Networks and Learning Systems (TNNLS); IJCAI'22 FTL workshop innovation award; code at https://github.com/microsoft/PersonalizedFL

It is expensive and time-consuming to collect sufficient labeled data to build human activity recognition (HAR) models. Training on existing data often makes the model biased towards the distribution of the training data, thus the model might perform terribly on test data with different distributions. Although existing efforts on transfer learning and domain adaptation try to solve the above problem, they still need access to unlabeled data on the target domain, which may not be possible in real scenarios. Few works pay attention to training a model that can generalize well to unseen target domains for HAR. In this paper, we propose a novel method called Semantic-Discriminative Mixup (SDMix) for generalizable cross-domain HAR. Firstly, we introduce semantic-aware Mixup that considers the activity semantic ranges to overcome the semantic inconsistency brought by domain differences. Secondly, we introduce the large margin loss to enhance the discrimination of Mixup to prevent misclassification brought by noisy virtual labels. Comprehensive generalization experiments on five public datasets demonstrate that our SDMix substantially outperforms the state-of-the-art approaches with 6% average accuracy improvement on cross-person, cross-dataset, and cross-position HAR., Comment: To be presented at UbiComp 2022; Accepted by Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)

Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization. However, we argue that existing methods might fail to utilize the unlabeled data more effectively since they either use a pre-defined / fixed threshold or an ad-hoc threshold adjusting scheme, resulting in inferior performance and slow convergence. We first analyze a motivating example to obtain intuitions on the relationship between the desirable threshold and model's learning status. Based on the analysis, we hence propose FreeMatch to adjust the confidence threshold in a self-adaptive manner according to the model's learning status. We further introduce a self-adaptive class fairness regularization penalty to encourage the model for diverse predictions during the early training stage. Extensive experiments indicate the superiority of FreeMatch especially when the labeled data are extremely rare. FreeMatch achieves 5.78%, 13.59%, and 1.28% error rate reduction over the latest state-of-the-art method FlexMatch on CIFAR-10 with 1 label per class, STL-10 with 4 labels per class, and ImageNet with 100 labels per class, respectively. Moreover, FreeMatch can also boost the performance of imbalanced SSL. The codes can be found at https://github.com/microsoft/Semi-supervised-learning., Comment: Accepted by ICLR 2023. Code: https://github.com/microsoft/Semi-supervised-learning

In image classification, it is often expensive and time-consuming to acquire sufficient labels. To solve this problem, domain adaptation often provides an attractive option given a large amount of labeled data from a similar nature but different domain. Existing approaches mainly align the distributions of representations extracted by a single structure and the representations may only contain partial information, e.g., only contain part of the saturation, brightness, and hue information. Along this line, we propose Multi-Representation Adaptation which can dramatically improve the classification accuracy for cross-domain image classification and specially aims to align the distributions of multiple representations extracted by a hybrid structure named Inception Adaptation Module (IAM). Based on this, we present Multi-Representation Adaptation Network (MRAN) to accomplish the cross-domain image classification task via multi-representation alignment which can capture the information from different aspects. In addition, we extend Maximum Mean Discrepancy (MMD) to compute the adaptation loss. Our approach can be easily implemented by extending most feed-forward models with IAM, and the network can be trained efficiently via back-propagation. Experiments conducted on three benchmark image datasets demonstrate the effectiveness of MRAN. The code has been available at https://github.com/easezyc/deep-transfer-learning., Comment: Neural Networks regular paper. Transfer Learning, Domain Adaptation

Unsupervised anomaly detection aims to build models to effectively detect unseen anomalies by only training on the normal data. Although previous reconstruction-based methods have made fruitful progress, their generalization ability is limited due to two critical challenges. First, the training dataset only contains normal patterns, which limits the model generalization ability. Second, the feature representations learned by existing models often lack representativeness which hampers the ability to preserve the diversity of normal patterns. In this paper, we propose a novel approach called Adaptive Memory Network with Self-supervised Learning (AMSL) to address these challenges and enhance the generalization ability in unsupervised anomaly detection. Based on the convolutional autoencoder structure, AMSL incorporates a self-supervised learning module to learn general normal patterns and an adaptive memory fusion module to learn rich feature representations. Experiments on four public multivariate time series datasets demonstrate that AMSL significantly improves the performance compared to other state-of-the-art methods. Specifically, on the largest CAP sleep stage detection dataset with 900 million samples, AMSL outperforms the second-best baseline by \textbf{4}\%+ in both accuracy and F1 score. Apart from the enhanced generalization ability, AMSL is also more robust against input noise., Comment: Accepted by IEEE Transactions on Knowledge and Data Engineering (TKDE) 2022; 13 pages

The long-tailed class distribution in visual recognition tasks poses great challenges for neural networks on how to handle the biased predictions between head and tail classes, i.e., the model tends to classify tail classes as head classes. While existing research focused on data resampling and loss function engineering, in this paper, we take a different perspective: the classification margins. We study the relationship between the margins and logits (classification scores) and empirically observe the biased margins and the biased logits are positively correlated. We propose MARC, a simple yet effective MARgin Calibration function to dynamically calibrate the biased margins for unbiased logits. We validate MARC through extensive experiments on common long-tailed benchmarks including CIFAR-LT, ImageNet-LT, Places-LT, and iNaturalist-LT. Experimental results demonstrate that our MARC achieves favorable results on these benchmarks. In addition, MARC is extremely easy to implement with just three lines of code. We hope this simple method will motivate people to rethink the biased margins and biased logits in long-tailed visual recognition., Comment: Accepted by Asian Conference on Machine Learning (ACML) 2022; 16 pages

There is a growing interest in applying machine learning techniques to healthcare. Recently, federated learning (FL) is gaining popularity since it allows researchers to train powerful models without compromising data privacy and security. However, the performance of existing FL approaches often deteriorates when encountering non-iid situations where there exist distribution gaps among clients, and few previous efforts focus on personalization in healthcare. In this article, we propose FedAP to tackle domain shifts and then obtain personalized models for local clients. FedAP learns the similarity between clients based on the statistics of the batch normalization layers while preserving the specificity of each client with different local batch normalization. Comprehensive experiments on five healthcare benchmarks demonstrate that FedAP achieves better accuracy compared to state-of-the-art methods (e.g., 10% accuracy improvement for PAMAP2) with faster convergence speed., Comment: Accepted by IEEE Transactions on Big Data; code: https://github.com/microsoft/personalizedfl. arXiv admin note: substantial text overlap with arXiv:2106.01009

The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised learning (SSL) benchmarks. However, like other modern SSL algorithms, FixMatch uses a pre-defined constant threshold for all classes to select unlabeled data that contribute to the training, thus failing to consider different learning status and learning difficulties of different classes. To address this issue, we propose Curriculum Pseudo Labeling (CPL), a curriculum learning approach to leverage unlabeled data according to the model's learning status. The core of CPL is to flexibly adjust thresholds for different classes at each time step to let pass informative unlabeled data and their pseudo labels. CPL does not introduce additional parameters or computations (forward or backward propagation). We apply CPL to FixMatch and call our improved algorithm FlexMatch. FlexMatch achieves state-of-the-art performance on a variety of SSL benchmarks, with especially strong performances when the labeled data are extremely limited or when the task is challenging. For example, FlexMatch achieves 13.96% and 18.96% error rate reduction over FixMatch on CIFAR-100 and STL-10 datasets respectively, when there are only 4 labels per class. CPL also significantly boosts the convergence speed, e.g., FlexMatch can use only 1/5 training time of FixMatch to achieve even better performance. Furthermore, we show that CPL can be easily adapted to other SSL algorithms and remarkably improve their performances. We open-source our code at https://github.com/TorchSSL/TorchSSL., Comment: NeurIPS 2021; camera-ready version; 16 pages with appendix; code: https://github.com/TorchSSL/TorchSSL

Self-supervised pre-training could effectively improve the performance of low-resource automatic speech recognition (ASR). However, existing self-supervised pre-training are task-agnostic, i.e., could be applied to various downstream tasks. Although it enlarges the scope of its application, the capacity of the pre-trained model is not fully utilized for the ASR task, and the learned representations may not be optimal for ASR. In this work, in order to build a better pre-trained model for low-resource ASR, we propose a pre-training approach called wav2vec-S, where we use task-specific semi-supervised pre-training to refine the self-supervised pre-trained model for the ASR task thus more effectively utilize the capacity of the pre-trained model to generate task-specific representations for ASR. Experiments show that compared to wav2vec 2.0, wav2vec-S only requires a marginal increment of pre-training time but could significantly improve ASR performance on in-domain, cross-domain and cross-lingual datasets. Average relative WER reductions are 24.5% and 6.6% for 1h and 10h fine-tuning, respectively. Furthermore, we show that semi-supervised pre-training could close the representation gap between the self-supervised pre-trained model and the corresponding fine-tuned model through canonical correlation analysis., Comment: Accepted by Interspeech 2022

Time series has wide applications in the real world and is known to be difficult to forecast. Since its statistical properties change over time, its distribution also changes temporally, which will cause severe distribution shift problem to existing methods. However, it remains unexplored to model the time series in the distribution perspective. In this paper, we term this as Temporal Covariate Shift (TCS). This paper proposes Adaptive RNNs (AdaRNN) to tackle the TCS problem by building an adaptive model that generalizes well on the unseen test data. AdaRNN is sequentially composed of two novel algorithms. First, we propose Temporal Distribution Characterization to better characterize the distribution information in the TS. Second, we propose Temporal Distribution Matching to reduce the distribution mismatch in TS to learn the adaptive TS model. AdaRNN is a general framework with flexible distribution distances integrated. Experiments on human activity recognition, air quality prediction, and financial analysis show that AdaRNN outperforms the latest methods by a classification accuracy of 2.6% and significantly reduces the RMSE by 9.0%. We also show that the temporal distribution matching algorithm can be extended in Transformer structure to boost its performance., Comment: Accepted by CIKM 2021 as a full paper; 10 pages; code at: https://github.com/jindongwang/transferlearning/tree/master/code/deep/adarnn

Nowadays, multi-sensor technologies are applied in many fields, e.g., Health Care (HC), Human Activity Recognition (HAR), and Industrial Control System (ICS). These sensors can generate a substantial amount of multivariate time-series data. Unsupervised anomaly detection on multi-sensor time-series data has been proven critical in machine learning researches. The key challenge is to discover generalized normal patterns by capturing spatial-temporal correlation in multi-sensor data. Beyond this challenge, the noisy data is often intertwined with the training data, which is likely to mislead the model by making it hard to distinguish between the normal, abnormal, and noisy data. Few of previous researches can jointly address these two challenges. In this paper, we propose a novel deep learning-based anomaly detection algorithm called Deep Convolutional Autoencoding Memory network (CAE-M). We first build a Deep Convolutional Autoencoder to characterize spatial dependence of multi-sensor data with a Maximum Mean Discrepancy (MMD) to better distinguish between the noisy, normal, and abnormal data. Then, we construct a Memory Network consisting of linear (Autoregressive Model) and non-linear predictions (Bidirectional LSTM with Attention) to capture temporal dependence from time-series data. Finally, CAE-M jointly optimizes these two subnetworks. We empirically compare the proposed approach with several state-of-the-art anomaly detection methods on HAR and HC datasets. Experimental results demonstrate that our proposed model outperforms these existing methods., Comment: Accepted to IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE) as a regular paper; 14 pages

For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and target distributions without considering the relationships between two subdomains within the same category of different domains, leading to unsatisfying transfer learning performance without capturing the fine-grained information. Recently, more and more researchers pay attention to Subdomain Adaptation which focuses on accurately aligning the distributions of the relevant subdomains. However, most of them are adversarial methods which contain several loss functions and converge slowly. Based on this, we present Deep Subdomain Adaptation Network (DSAN) which learns a transfer network by aligning the relevant subdomain distributions of domain-specific layer activations across different domains based on a local maximum mean discrepancy (LMMD). Our DSAN is very simple but effective which does not need adversarial training and converges fast. The adaptation can be achieved easily with most feed-forward network models by extending them with LMMD loss, which can be trained efficiently via back-propagation. Experiments demonstrate that DSAN can achieve remarkable results on both object recognition tasks and digit classification tasks. Our code will be available at: https://github.com/easezyc/deep-transfer-learning, Comment: published on TNNLS

The success of machine learning applications often needs a large quantity of data. Recently, federated learning (FL) is attracting increasing attention due to the demand for data privacy and security, especially in the medical field. However, the performance of existing FL approaches often deteriorates when there exist domain shifts among clients, and few previous works focus on personalization in healthcare. In this article, we propose FedHealth 2, an extension of FedHealth \cite{chen2020fedhealth} to tackle domain shifts and get personalized models for local clients. FedHealth 2 obtains the client similarities via a pretrained model, and then it averages all weighted models with preserving local batch normalization. Wearable activity recognition and COVID-19 auxiliary diagnosis experiments have evaluated that FedHealth 2 can achieve better accuracy (10%+ improvement for activity recognition) and personalized healthcare without compromising privacy and security., Comment: Accepted by IJCAI-21 workshop on federated learning

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition models can easily overfit. In this paper, we propose to use adapters to investigate the performance of multiple adapters for parameter-efficient cross-lingual speech adaptation. Based on our previous MetaAdapter that implicitly leverages adapters, we propose a novel algorithms called SimAdapter for explicitly learning knowledge from adapters. Our algorithm leverages adapters which can be easily integrated into the Transformer structure.MetaAdapter leverages meta-learning to transfer the general knowledge from training data to the test language. SimAdapter aims to learn the similarities between the source and target languages during fine-tuning using the adapters. We conduct extensive experiments on five-low-resource languages in Common Voice dataset. Results demonstrate that our MetaAdapter and SimAdapter methods can reduce WER by 2.98% and 2.55% with only 2.5% and 15.5% of trainable parameters compared to the strong full-model fine-tuning baseline. Moreover, we also show that these two novel algorithms can be integrated for better performance with up to 3.55% relative WER reduction., Comment: Accepted by IEEE Transactions on Audio, Speech, and Language Processing (TASLP) as a full paper; 12 pages; code at https://github.com/jindongwang/transferlearning/tree/master/code/ASR/Adapter

End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data. However, it is known that domain mismatch between training and testing data often leads to a degradation of recognition accuracy. In this work, we focus on the unsupervised domain adaptation for ASR and propose CMatch, a Character-level distribution matching method to perform fine-grained adaptation between each character in two domains. First, to obtain labels for the features belonging to each character, we achieve frame-level label assignment using the Connectionist Temporal Classification (CTC) pseudo labels. Then, we match the character-level distributions using Maximum Mean Discrepancy. We train our algorithm using the self-training technique. Experiments on the Libri-Adapt dataset show that our proposed approach achieves 14.39% and 16.50% relative Word Error Rate (WER) reduction on both cross-device and cross-environment ASR. We also comprehensively analyze the different strategies for frame-level label assignment and Transformer adaptations., Comment: Accepted to INTERSPEECH 2021; code available at https://github.com/jindongwang/transferlearning/tree/master/code/ASR/CMatch

Being expensive and time-consuming to collect massive COVID-19 image samples to train deep classification models, transfer learning is a promising approach by transferring knowledge from the abundant typical pneumonia datasets for COVID-19 image classification. However, negative transfer may deteriorate the performance due to the feature distribution divergence between two datasets and task semantic difference in diagnosing pneumonia and COVID-19 that rely on different characteristics. It is even more challenging when the target dataset has no labels available, i.e., unsupervised task transfer learning. In this paper, we propose a novel Task Adaptation Network (TAN) to solve this unsupervised task transfer problem. In addition to learning transferable features via domain-adversarial training, we propose a novel task semantic adaptor that uses the learning-to-learn strategy to adapt the task semantics. Experiments on three public COVID-19 datasets demonstrate that our proposed method achieves superior performance. Especially on COVID-DA dataset, TAN significantly increases the recall and F1 score by 5.0% and 7.8% compared to recently strong baselines. Moreover, we show that TAN also achieves superior performance on several public domain adaptation benchmarks., Comment: Technical report, 12 pages

Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen distributions. Domain generalization (DG), i.e., out-of-distribution generalization, has attracted increasing interests in recent years. Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain. Great progress has been made in the area of domain generalization for years. This paper presents the first review of recent advances in this area. First, we provide a formal definition of domain generalization and discuss several related fields. We then thoroughly review the theories related to domain generalization and carefully analyze the theory behind generalization. We categorize recent algorithms into three classes: data manipulation, representation learning, and learning strategy, and present several popular algorithms in detail for each category. Third, we introduce the commonly used datasets, applications, and our open-sourced codebase for fair evaluation. Finally, we summarize existing literature and present some potential research topics for the future., Comment: Accepted by IEEE Trans. on Knowledge and Data Engineering (TKDE); 19 pages; short version (6 pages) is accepted by IJCAI-21 survey track; codebase: https://github.com/jindongwang/transferlearning/tree/master/code/DeepDG

In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features (e.g., mel-spectrograms or MFCC) as the input, and recognizing both text sequences, where the two recognition losses use the same combination weight. We apply MixSpeech on two popular end-to-end speech recognition models including LAS (Listen, Attend and Spell) and Transformer, and conduct experiments on several low-resource datasets including TIMIT, WSJ, and HKUST. Experimental results show that MixSpeech achieves better accuracy than the baseline models without data augmentation, and outperforms a strong data augmentation method SpecAugment on these recognition tasks. Specifically, MixSpeech outperforms SpecAugment with a relative PER improvement of 10.6$\%$ on TIMIT dataset, and achieves a strong WER of 4.7$\%$ on WSJ dataset., Comment: To appear at ICASSP 2021