Speech emotion recognition is crucial to human-computer interaction. The temporal regions that represent different emotions scatter in different parts of the speech locally. Moreover, the temporal scales of important information may vary over a large range within and across speech segments. Although transformer-based models have made progress in this field, the existing models could not precisely locate important regions at different temporal scales. To address the issue, we propose Dynamic Window transFormer (DWFormer), a new architecture that leverages temporal importance by dynamically splitting samples into windows. Self-attention mechanism is applied within windows for capturing temporal important information locally in a fine-grained way. Cross-window information interaction is also taken into account for global communication. DWFormer is evaluated on both the IEMOCAP and the MELD datasets. Experimental results show that the proposed model achieves better performance than the previous state-of-the-art methods.
Enabled by multi-head self-attention, Transformer has exhibited remarkable results in speech emotion recognition (SER). Compared to the original full attention mechanism, window-based attention is more effective in learning fine-grained features while greatly reducing model redundancy. However, emotional cues are present in a multi-granularity manner such that the pre-defined fixed window can severely degrade the model flexibility. In addition, it is difficult to obtain the optimal window settings manually. In this paper, we propose a Deformable Speech Transformer, named DST, for SER task. DST determines the usage of window sizes conditioned on input speech via a light-weight decision network. Meanwhile, data-dependent offsets derived from acoustic features are utilized to adjust the positions of the attention windows, allowing DST to adaptively discover and attend to the valuable information embedded in the speech. Extensive experiments on IEMOCAP and MELD demonstrate the superiority of DST.
Paralinguistic speech processing is important in addressing many issues, such as sentiment and neurocognitive disorder analyses. Recently, Transformer has achieved remarkable success in the natural language processing field and has demonstrated its adaptation to speech. However, previous works on Transformer in the speech field have not incorporated the properties of speech, leaving the full potential of Transformer unexplored. In this paper, we consider the characteristics of speech and propose a general structure-based framework, called SpeechFormer++, for paralinguistic speech processing. More concretely, following the component relationship in the speech signal, we design a unit encoder to model the intra- and inter-unit information (i.e., frames, phones, and words) efficiently. According to the hierarchical relationship, we utilize merging blocks to generate features at different granularities, which is consistent with the structural pattern in the speech signal. Moreover, a word encoder is introduced to integrate word-grained features into each unit encoder, which effectively balances fine-grained and coarse-grained information. SpeechFormer++ is evaluated on the speech emotion recognition (IEMOCAP & MELD), depression classification (DAIC-WOZ) and Alzheimer's disease detection (Pitt) tasks. The results show that SpeechFormer++ outperforms the standard Transformer while greatly reducing the computational cost. Furthermore, it delivers superior results compared to the state-of-the-art approaches.
Referring video object segmentation aims to segment the object referred by a given language expression. Existing works typically require compressed video bitstream to be decoded to RGB frames before being segmented, which increases computation and storage requirements and ultimately slows the inference down. This may hamper its application in real-world computing resource limited scenarios, such as autonomous cars and drones. To alleviate this problem, in this paper, we explore the referring object segmentation task on compressed videos, namely on the original video data flow. Besides the inherent difficulty of the video referring object segmentation task itself, obtaining discriminative representation from compressed video is also rather challenging. To address this problem, we propose a multi-attention network which consists of dual-path dual-attention module and a query-based cross-modal Transformer module. Specifically, the dual-path dual-attention module is designed to extract effective representation from compressed data in three modalities, i.e., I-frame, Motion Vector and Residual. The query-based cross-modal Transformer firstly models the correlation between linguistic and visual modalities, and then the fused multi-modality features are used to guide object queries to generate a content-aware dynamic kernel and to predict final segmentation masks. Different from previous works, we propose to learn just one kernel, which thus removes the complicated post mask-matching procedure of existing methods. Extensive promising experimental results on three challenging datasets show the effectiveness of our method compared against several state-of-the-art methods which are proposed for processing RGB data. Source code is available at: https://github.com/DexiangHong/MANet.
Transformer has obtained promising results on cognitive speech signal processing field, which is of interest in various applications ranging from emotion to neurocognitive disorder analysis. However, most works treat speech signal as a whole, leading to the neglect of the pronunciation structure that is unique to speech and reflects the cognitive process. Meanwhile, Transformer has heavy computational burden due to its full attention operation. In this paper, a hierarchical efficient framework, called SpeechFormer, which considers the structural characteristics of speech, is proposed and can be served as a general-purpose backbone for cognitive speech signal processing. The proposed SpeechFormer consists of frame, phoneme, word and utterance stages in succession, each performing a neighboring attention according to the structural pattern of speech with high computational efficiency. SpeechFormer is evaluated on speech emotion recognition (IEMOCAP & MELD) and neurocognitive disorder detection (Pitt & DAIC-WOZ) tasks, and the results show that SpeechFormer outperforms the standard Transformer-based framework while greatly reducing the computational cost. Furthermore, our SpeechFormer achieves comparable results to the state-of-the-art approaches.
Long-term scene changes present challenges to localization systems using a pre-built map. This paper presents a LiDAR-based system that can provide robust localization against those challenges. Our method starts with activation of a mapping process temporarily when global matching towards the pre-built map is unreliable. The temporary map will be merged onto the pre-built map for later localization runs once reliable matching is obtained again. We further integrate a LiDAR inertial odometry (LIO) to provide motion-compensated LiDAR scans and a reliable initial pose guess for the global matching module. To generate a smooth real-time trajectory for navigation purposes, we fuse poses from odometry and global matching by solving a pose graph optimization problem. We evaluate our localization system with extensive experiments on the NCLT dataset including a variety of changing indoor and outdoor environments, and the results demonstrate a robust and accurate localization performance for over a year. The implementations are open sourced on GitHub.
Speech emotion recognition is a challenging and important research topic that plays a critical role in human-computer interaction. Multimodal inputs can improve the performance as more emotional information is used for recognition. However, existing studies learnt all the information in the sample while only a small portion of it is about emotion. Moreover, under the multimodal framework, the interaction between different modalities is shallow and insufficient. In this paper, a keysparse Transformer is proposed for efficient SER by only focusing on emotion related information. Furthermore, a cascaded cross-attention block, which is specially designed for multimodal framework, is introduced to achieve deep interaction between different modalities. The proposed method is evaluated by IEMOCAP corpus and the experimental results show that the proposed method gives better performance than the state-of-theart approaches.
A new unsupervised learning method of depth and ego-motion using multiple masks from monocular video is proposed in this paper. The depth estimation network and the ego-motion estimation network are trained according to the constraints of depth and ego-motion without truth values. The main contribution of our method is to carefully consider the occlusion of the pixels generated when the adjacent frames are projected to each other, and the blank problem generated in the projection target imaging plane. Two fine masks are designed to solve most of the image pixel mismatch caused by the movement of the camera. In addition, some relatively rare circumstances are considered, and repeated masking is proposed. To some extent, the method is to use a geometric relationship to filter the mismatched pixels for training, making unsupervised learning more efficient and accurate. The experiments on KITTI dataset show our method achieves good performance in terms of depth and ego-motion. The generalization capability of our method is demonstrated by training on the low-quality uncalibrated bike video dataset and evaluating on KITTI dataset, and the results are still good.
Speech emotion recognition is a vital contributor to the next generation of human-computer interaction (HCI). However, current existing small-scale databases have limited the development of related research. In this paper, we present LSSED, a challenging large-scale english speech emotion dataset, which has data collected from 820 subjects to simulate real-world distribution. In addition, we release some pre-trained models based on LSSED, which can not only promote the development of speech emotion recognition, but can also be transferred to related downstream tasks such as mental health analysis where data is extremely difficult to collect. Finally, our experiments show the necessity of large-scale datasets and the effectiveness of pre-trained models. The dateset will be released on https://github.com/tobefans/LSSED.
Visual localization is a crucial component in the application of mobile robot and autonomous driving. Image retrieval is an efficient and effective technique in image-based localization methods. Due to the drastic variability of environmental conditions, e.g.Su illumination, seasonal and weather changes, retrieval-based visual localization is severely affected and becomes a challenging problem. In this work, a general architecture is first formulated probabilistically to extract domain-invariant feature through multi-domain image translation. And then a novel gradient-weighted similarity activation mapping loss (Grad-SAM) is incorporated for finer localization with high accuracy. We also propose a new adaptive triplet loss to boost the metric learning of the embedding in a self-supervised manner. The final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models without and with Grad-SAM loss. Extensive experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons dataset. The strong generalization ability of our approach is verified on RobotCar dataset using models pre-trained on urban part of CMU-Seasons dataset. Our performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision, especially under the challenging environments with illumination variance, vegetation and night-time images.