33 accepted papers
In speech deepfake detection (SDD), data augmentation (DA) is commonly used to improve model generalization across varied speech conditions and spoofing attacks. However, during training, the backpropagated gradients from original and augmented inputs may misalign, which can result in conflicting pa…
Achieving precise and controllable emotional expression is crucial for producing natural and context-appropriate speech in text-to-speech (TTS) synthesis. However, many emotion-aware TTS systems, including large language model (LLM)-based designs, rely on scaling fixed emotion embeddings or external…
Autoregressive learning of time-stepping operators offers an effective approach to data-driven PDE simulation on grids. For conservation laws, however, long-horizon rollouts are often destabilized when learned updates violate global conservation and, in many applications, additional state bounds—suc…
LLM-based ASR overcomes multilingual data scarcity by projecting speech representations into the LLM space to leverage its robust semantic and reasoning capabilities. However, while previous approaches typically enhance performance by scaling data or model parameters, a single projector often strugg…
Recent advancements in long chain-of-thought (CoT) reasoning, particularly through the Group Relative Policy Optimization algorithm used by DeepSeek-R1, have led to significant interest in the potential of Reinforcement Learning with Verifiable Rewards (RLVR) for Large Language Models (LLMs). While…
Recent advances in Speech Large Language Models (Speech LLMs) have paved the way for unified architectures across diverse speech understanding tasks. However, prevailing alignment paradigms rely heavily on large-scale audio-text paired data and computationally intensive training, yet often exhibit l…
Few-shot Semantic Segmentation (FSS) aims to segment the novel target objects with the guidance of minimal annotated reference examples. The affinity-based method has great advantages in the FSS inference stage for both specialist model and foundation model. However, current affinity calculation me
Recently, video-language models (VidLMs) have gained widespread attention and adoption. However, existing works primarily focus on terrestrial scenarios, overlooking the highly demanding application needs of underwater observation. To overcome this gap, we introduce UVLM, an under water observation
There are various factors that can influence the performance of speaker recognition systems, such as emotion, language and other speaker-related or context-related variations. Since individual speech frames do not contribute equally to the utterance-level representation, it is essential to estimate…
Multi-agent systems (MAS) have shown great potential in executing complex tasks, but coordination and safety remain significant challenges. Multi-Agent Reinforcement Learning (MARL) offers a promising framework for agent collaboration, but it faces difficulties in handling complex tasks and designin
Modality exploration has been repeatedly mentioned in gait recognition, evolving from silhouette to parsing, mesh, point clouds, etc. These latest modalities agree that silhouette is less affected by background and clothing noises, but argue it loses too much valuable discriminative information. The…
Generative models aim to simulate realistic effects of various actions across different contexts, from text generation to visual effects. Despite significant efforts to build real-world simulators, the application of generative models to virtual worlds, like financial markets, remains under-explored…
Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In th…
Object Navigation (ObjectNav) is a fundamental task in embodied artificial intelligence. Although significant progress has been made in semantic map construction and target direction prediction in current research, redundant exploration and exploration failures remain inevitable. A critical but unde…
The significant differences in the physical properties of air and water pose a substantial challenge for the development of hybrid aerial-aquatic vehicle (HAAV), which leading to increased prototype size, heavier thrusters, and reduced efficiency or under-actuation in one of the mediums. This letter
Industrial robots and collaborative robots are widely employed in industry and are progressively being utilized to assist individuals in their daily routines. To improve their absolute accuracy, self-calibration methods using portable local measurement devices are cost-effective solutions. However,…
Target speaker extraction aims to extract the speech of a specific speaker from a multi-talker mixture as specified by an auxiliary reference. Most studies focus on the scenario where the target speech is highly overlapped with the interfering speech. However, this scenario only accounts for a small…
Contrastive learning has shown impressive success in enhancing feature discriminability for various visual tasks in a self-supervised manner, but the standard contrastive paradigm (features+l2 normalization) has limited benefits when applied in domain adaptation. We find that this is mainly because…
Zero-shot voice conversion (VC) aims to transfer the source speaker timbre to arbitrary unseen target speaker timbre, while keeping the linguistic content unchanged. Although the voice of generated speech can be controlled by providing the speaker embedding of the target speaker, the speaker similar…
"In this work, we focus on the cross-domain few-shot classification (CDFSC), which is mostly challenged by the low-data problem as well as extreme domain shift between base and novel target classes. Current methods always employ a lightweight backbone and continue to use a linear-probe-like traditio…
The existing weakly supervised semantic segmentation (WSSS) methods pay much attention to generating accurate and complete class activation maps (CAMs) as pseudo-labels, while ignoring the importance of training the segmentation networks. In this work, we observe that there is an inconsistency betwe…
Out-of-distribution (OOD) detection aims at enhancing standard deep neural networks to distinguish anomalous inputs from original training data. Previous progress has introduced various approaches where the in-distribution training data and even several OOD examples are prerequisites. However, due t…
Domain adaptive semantic segmentation aims to exploit the pixel-level annotated samples on source domain to assist the segmentation of unlabeled samples on target domain. For such a task, the key is to construct reliable supervision signals on target domain. However, existing methods can only provid…
Detecting out-of-distribution (OOD) examples is crucial to guarantee the reliability and safety of deep neural networks in real-world settings. In this paper, we offer an innovative perspective on quantifying the disparities between in-distribution (ID) and OOD data---analyzing the uncertainty that…
Weakly-supervised temporal action localization aims to localize action instances in videos with only video-level action labels. Existing methods mainly embrace a localization-by-classification pipeline that optimizes the snippet-level prediction with a video classification loss. However, this formul…
Machine learning applications of 3D audio are gaining increasing interest in recent years. In this paper, we propose a stream attention based U-Net to remove background noise and reverberation based on ICASSP Signal Processing Grand Challenge 2023: L3DAS23 Challenge<sup xmlns:mml="http://www.w3.org/…
Domain adaptation (DA) aims to transfer knowledge from a label-rich source domain to a related but label-scarce target domain. Recently, increasing research has focused on exploring data structure of the target domain. In light of the recent success of Instance Discrimination Contrastive (IDCo) loss…
"Person search is a challenging task which aims to achieve joint pedestrian detection and person re-identification (ReID). Previous works have made significant advances under fully and weakly supervised settings. However, existing methods ignore the generalization ability of the person search models…
As a fundamental task in opinion mining, aspect and opinion co-extraction aims to identify the aspect terms and opinion terms in reviews. However, due to the lack of fine-grained annotated resources, it is hard to train a robust model for many domains. To alleviate this issue, unsupervised domain ad…
Targeted Multimodal Sentiment Classification (TMSC) aims to identify the sentiment polarities over each target mentioned in a pair of sentence and image. Existing methods to TMSC failed to explicitly capture both coarse-grained and fine-grained image-target matching, including 1) the relevance betwe…
Text Normalization (TN) is an essential part in conversational systems like text-to-speech synthesis (TTS) and automatic speech recognition (ASR). It is a process of transforming non-standard words (NSW) into a representation of how the words are to be spoken. Existing approaches to TN are mainly ru…
Few-shot classification aims to categorize the samples from unseen classes with only few labeled samples. To address such a challenge, many methods exploit a base set consisting of massive labeled samples to learn an instance embedding function, i.e., image feature extractor, and it is expected to p…
Chinese Spelling Check (CSC) is a challenging task due to the complex characteristics of Chinese characters. Statistics reveal that most Chinese spelling errors belong to phonological or visual errors. However, previous methods rarely utilize phonological and morphological knowledge of Chinese chara…