93 accepted papers
Fairness in Continual Learning for Large Multimodal Models (LMMs) is an emerging yet underexplored challenge, particularly in the presence of imbalanced data distributions that can lead to biased model updates and suboptimal performance across tasks. While recent continual learning studies have made
Precisely evaluating video understanding models remains challenging: commonly used metrics such as BLEU, ROUGE, and BERTScore fail to capture the fineness of human judgment, while obtaining such judgments through manual evaluation is costly. Recent work has explored using large language models (LLMs…
Understanding and explaining differences between audio recordings is crucial for fields like audio forensics, quality assessment, and audio generation. This involves identifying and describing audio events, acoustic scenes, signal characteristics, and their emotional impact on listeners. This paper…
Recent literature uses language to build foundation models for audio. These Audio-Language Models (ALMs) are trained on a vast number of audio-text pairs and show remarkable performance in tasks including Text-to-Audio Retrieval, Captioning, and Question Answering. However, their ability to engage i…
Speaker verification is a typical zero-shot learning task, where inference of unseen classes is performed by comparing embeddings of test instances to known examples. The models performing inference must hence naturally generate embeddings that cluster same-class instances compactly, while maintaini
Large multimodal models (LMMs) have gained impressive performance due to their outstanding capability in various understanding tasks. However, these models still suffer from some fundamental limitations related to robustness and generalization due to the alignment and correlation between visual and…
Continual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge. Prior studies focused on modeling the catastrophic forgetting and background shift challenges in continual learning. However, fairnes…
Image tokenizers are crucial for visual generative models, \eg, diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. Increasing token length is a common approach to improve image reconstruction quality. However, tokenizers with longer token…
Speech foundation models trained at a massive scale, both in terms of model and data size, result in robust systems capable of performing multiple speech tasks, including automatic speech recognition (ASR). These models transcend language and domain barriers, yet effectively measuring their performa…
Recent advances in latent diffusion models have demonstrated their effectiveness for high-resolution image synthesis. However, the properties of the latent space from tokenizer for better learning and generation of diffusion models remain under-explored. Theoretically and empirically, we find that i…
Multimodal Audio-Language Models (ALMs) can understand and reason over both audio and text. Typically, reasoning performance correlates with model size, with the best results achieved by models exceeding 8 billion parameters. However, no prior work has explored enabling small audio-language models t…
Unified multimodal large language models (U-MLLMs) have demonstrated impressive performance in end-to-end visual understanding and generation tasks. However, compared to generation-only systems (e.g., Stable Diffusion), the unified architecture of U-MLLMs introduces new risks of propagating demograp…
Recent advances in speech foundation models are largely driven by scaling both model size and data, enabling them to perform a wide range of tasks, including speech recognition. Traditionally, ASR models are evaluated using metrics like Word Error Rate (WER) and Character Error Rate (CER), which dep…
Vocabulary acquisition poses a significant challenge for second-language (L2) learners, especially when learning typologically distant languages such as English and Korean, where phonological and structural mismatches complicate vocabulary learning. Recently, large language models (LLMs) have been u
Automatic Speech Recognition (ASR) systems must be robust to the myriad types of noises present in real-world environments including environmental noise, room impulse response, special effects as well as attacks by malicious actors (adversarial attacks). Recent works seek to improve accuracy and rob…
Speaker verification (SV) models are increasingly integrated into security, personalization, and access control systems, yet their robustness to many real-world challenges remains inadequately benchmarked. Real-world systems can face diverse conditions, some naturally occurring, and others that may
We aim to redefine robust ego-motion estimation and photorealistic 3D reconstruction by addressing a critical limitation: the reliance on noise-free data in existing models. While such sanitized conditions simplify evaluation, they fail to capture the unpredictable, noisy complexities of real-world…
Efficient image tokenization with high compression ratios remains a critical challenge for training generative models.We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple codewords into each latent token, substantially increasing the re…
As Automatic Speech Recognition (ASR) models become ever more pervasive, it is important to ensure that they make reliable predictions under corruptions present in the physical and digital world. We propose Speech Robust Bench (SRB), a comprehensive benchmark for evaluating the robustness of ASR mo…
Voice biometric tasks, such as age estimation require modelling the often complex relationship between voice features and the biometric variable. While deep learning models can handle such complexity, they typically require large amounts of accurately labeled data to perform well. Such data are ofte…
System identification from videos aims to recover object geometry and governing physical laws. Existing methods integrate differentiable rendering with simulation but rely on predefined material priors, limiting their ability to handle unknown ones. We introduce MASIV, the first vision-based framewo…
We contribute an unsupervised method that effectively learns disentangled content and style representations from sequences of observations. Unlike most disentanglement algorithms that rely on domain-specific labels or knowledge, our method is based on the insight of domain-general statistical differ…
Recent work on distilling Whisper’s knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50%. This results in small, efficient, and dedicated models. However, a critical step of distillation using pseudo-labels involves filtering high-quality p…
Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment. This paper introduces a general framework for learning from weak supe…
Abstractive speech summarization (SSUM) aims to generate humanlike summaries from speech. Given variations in information captured and phrasing, recordings can be summarized in multiple ways. Therefore, it is more reasonable to consider a probabilistic distribution of all potential summaries rather…
Recent advancements in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet their reliance on extensive manual labeling to provide procedural feedback remains a significant impediment. To address this challenge, in this paper, we propose a novel self-supervised framewor…
This paper presents a novel approach to object completion, with the primary goal of reconstructing a complete object from its partially visible components. Our method, named MaskComp, delineates the completion process through iterative stages of generation and segmentation. In each iteration, the ob…
Recently, neural networks have shown impressive progress across diverse fields, with speech processing being no exception. However, recent breakthroughs in this area require extensive offline training using large datasets and tremendous computing resources. Unfortunately, these models struggle to re…
Unsupervised Domain Adaptation has been an efficient approach to transferring the semantic segmentation model across data distributions. Meanwhile, the recent Open-vocabulary Semantic Scene understanding based on large-scale vision language models is effective in open-set settings because it can lea…
Vulnerability to adversarial perturbations is a major flaw of Deep Neural Networks (DNNs) that brings their reliability in real-world scenarios into question. However, biological perception, which DNNs emulate, is highly robust to such perturbations. This suggests that DNNs diverge from biological p…
Weak-label learning is a challenging task that requires learning from data "bags" containing positive and negative instances, but only the bag labels are known. The pool of negative instances is usually larger than positive instances, thus making selecting the most informative negative instance crit…
Learning with reduced labeling standards, such as noisy label, partial label, and supplementary unlabeled data, which we generically refer to as imprecise label, is a commonplace challenge in machine learning tasks. Previous methods tend to propose specific designs for every emerging imprecise label…
Continual learning, which aims to incrementally accumulate knowledge, has been an increasingly significant but challenging research topic for deep models that are prone to catastrophic forgetting. In this paper, we propose a novel replay-based continual learning approach in the context of class-incr…
Monocular depth estimation (MDE) is fundamental for deriving 3D scene structures from 2D images. While state-of-the-art monocular relative depth estimation (MRDE) excels in estimating relative depths for in-the-wild images, current monocular metric depth estimation (MMDE) approaches still face chall…
Emotions lie on a continuum, but current models treat emotions as a finite valued discrete variable. This representation does not capture the diversity in the expression of emotion. To better represent emotions we propose the use of natural language descriptions (or prompts). In this work, we addres…
Audiovisual segmentation (AVS) is a challenging task that aims to segment visual objects in videos according to their associated acoustic cues. With multiple sound sources and background disturbances involved establishing robust correspondences between audio and visual contents poses unique challeng…
End-to-end speech summarization on long recordings is challenging because of the high computational cost. Block-wise Adaptation for Speech Summarization (BASS) summarizes arbitrarily long sequences by sequentially processing abutting chunks of audio. Despite the benefits of BASS, it has higher compu…
"Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite progress in this field, the robustness of referring perception…
Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on large-scale datasets, including web-crawled data with paired data and conditions, such as image-text and image-class p…
Reference summaries for abstractive speech summarization require human annotation, which can be performed by listening to an audio recording or by reading textual transcripts of the recording. In this paper, we examine whether summaries based on annotators listening to the recordings differ from tho…
Remarkable strides have been made in reconstructing static scenes or human bodies from monocular videos. Yet the two problems have largely been approached independently without much synergy. Most visual SLAM methods can only reconstruct camera trajectories and scene structures up to scale while most…
Automated Audio Captioning (AAC) is the task of generating natural language descriptions given an audio stream. A typical AAC system requires manually curated training data of audio segments and corresponding text caption annotations. The creation of these audio-caption pairs is costly, resulting in…
Pre-training on large-scale datasets and then fine-tuning on downstream tasks have become a standard practice in deep learning. However, pre-training data often contain label noise that may adversely affect the generalization of the model. This paper aims to understand the nature of noise in pre-tra…
Speech enhancement aims to improve the quality of speech signals in terms of quality and intelligibility, and speech editing refers to the process of editing the speech according to specific user needs. In this paper, we propose a Unified Speech Enhancement and Editing (uSee) model with conditional…
Ontologies encompass a formal representation of knowledge through the definition of concepts or properties of a domain, and the relationships between those concepts. In this work, we seek to investigate whether using this ontological information will improve learning from weakly labeled data, which…
Although Domain Adaptation in Semantic Scene Segmentation has shown impressive improvement in recent years, the fairness concerns in the domain adaptation have yet to be well defined and addressed. In addition, fairness is one of the most critical aspects when deploying the segmentation models into…
Continual semantic segmentation aims to learn new classes while maintaining the information from the previous classes. Although prior studies have shown impressive progress in recent years, the fairness concern in the continual semantic segmentation needs to be better addressed. Meanwhile, fairness…
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…
Robustness to adversarial attacks is typically evaluated with adversarial accuracy. While essential, this metric does not capture all aspects of robustness and in particular leaves out the question of how many perturbations can be found for each point. In this work, we introduce an alternative appro…
Despite rapid advancement in recent years, current speech enhancement models often produce speech that differs in perceptual quality from real clean speech. We propose a learning objective that formalizes differences in perceptual quality, by using domain knowledge of acoustic-phonetics. We identify…
The paper introduces PaintSeg, a new unsupervised method for segmenting objects without any training. We propose an adversarial masked contrastive painting (AMCP) process, which creates a contrast between the original image and a painted image in which a masked area is painted using off-the-shelf ge…
In this paper, we focus on a general yet important learning problem, pairwise similarity learning (PSL). PSL subsumes a wide range of important applications, such as open-set face recognition, speaker verification, image retrieval and person re-identification. The goal of PSL is to learn a pairwise…
Video salient object detection (VSOD), as a fundamental computer vision problem, has been extensively discussed in the last decade. However, all existing works focus on addressing the VSOD problem in 2D scenarios. With the rapid development of VR devices, panoramic videos have been a promising alter…
Automatic Speaker Diarization (ASD) is an enabling technology with numerous applications, which deals with recordings of multiple speakers, raising special concerns in terms of privacy. In fact, in remote settings, where recordings are shared with a server, clients relinquish not only the privacy of…
Referring Video Object Segmentation (R-VOS) is a challenging task that aims to segment an object in a video based on a linguistic expression. Most existing R-VOS methods have a critical assumption: the object referred to must appear in the video. This assumption, which we refer to as "semantic conse…
The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling methods via a unified sample weighting formulatio…
Speech enhancement models have greatly progressed in recent years, but still show limits in perceptual quality of their speech outputs. We propose an objective for perceptual quality based on temporal acoustic parameters. These are fundamental speech features that play an essential role in various a…
This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a next-token prediction task and directly fine-tune the base LM to pe…
Linguistic communication is prevalent in Human-Computer Interaction (HCI). Speech (spoken language) serves as a convenient yet potentially ambiguous form due to noise and accents, exposing a gap compared to text. In this study, we investigate the prominent HCI task, Referring Video Object Segmentati…
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks -- subtle, perceptually indistinguishable perturbations of inputs that change the response of the model. In the context of vision, we hypothesize that an important contributor to the robustness of human visual perce…
Video Paragraph Captioning aims to generate a multi-sentence description of an untrimmed video with multiple temporal event locations in a coherent storytelling. Following the human perception process, where the scene is effectively understood by decomposing it into visual (e.g. human, animal) and…
Audio-visual segmentation is a challenging task that aims to predict pixel-level masks for sound sources in a video. Previous work applied a comprehensive manually designed architecture with countless pixel-wise accurate masks as supervision. However, these pixel-level masks are expensive and not…
State-of-the-art deep face recognition methods are mostly trained with a softmax-based multi-class classification framework. Despite being popular and effective, these methods still have a few shortcomings that limit empirical performance. In this paper, we start by identifying the discrepancy betwe…
Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural netw…
This paper studies the problem of learning self-supervised representations on videos. In contrast to image modality that only requires appearance information on objects or scenes, video needs to further explore the relations between multiple frames/clips along the temporal dimension. However, the re…
Speaker identification models are vulnerable to carefully designed adversarial perturbations of their input signals that induce misclassification. In this work, we propose a white-box steganography-inspired adversarial attack that generates imperceptible adversarial perturbations against a speaker i…
Recent work suggests that adversarial examples are enabled by high-frequency components in the dataset. In the speech domain where spectrograms are used extensively, masking those components seems like a sound direction for defenses against attacks. We explore a smoothing approach based on additive…
We present a conditional estimation (CEST) framework to learn 3D facial parameters from 2D single-view images by self-supervised training from videos. CEST is based on the process of analysis by synthesis, where the 3D facial parameters (shape, reflectance, viewpoint, and illumination) are estimated…
While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks, the Randomized Smoothing paradigm has been shown to be effec…
Turn-taking has played an essential role in structuring the regulation of a conversation. The task of identifying the main speaker (who is properly taking his/her turn of speaking) and the interrupters (who are interrupting or reacting to the main speaker's utterances) remains a challenging task. Al…
Automatic detection of speech affecting (SA) diseases has received significant attention, particularly in clinical scenarios. However, the same task in in-the-wild conditions is often neglected, in part, due to the lack of appropriate datasets.In this work, we present the in-the-Wild Speech Medical…
Deep Neural Networks (DNNs), while providing state-of-the-art performance in a wide variety of tasks, have been shown to be vulnerable to adversarial attacks. Recent studies have posited that this vulnerability arises because DNNs operate over a grossly overspecified input space with very sparse hum…
It is common practice to use pretrained image recognition models to compute feature representations for visual data. The size of the feature representations can have a noticeable impact on the complexity of the models that use these representations, and by extension on their deployablity and scalabi…
Normalization operations are widely used to train deep neural networks, and they can improve both convergence and generalization in most tasks. The theories for normalization's effectiveness and new forms of normalization have always been hot topics in research. To better understand normalization, o…
Existing audio search engines use one of two approaches: matching text-text or audio-audio pairs. In the former, text queries are matched to semantically similar words in an index of audio metadata to retrieve corresponding audio clips or segments, while in the latter, audio signals are directly use…
We propose a novel framework, called Disjoint Mapping Network (DIMNet), for cross-modal biometric matching, in particular of voices and faces. Different from the existing methods, DIMNet does not explicitly learn the joint relationship between the modalities. Instead, DIMNet learns a shared represen…
Voice profiling aims at inferring various human parameters from their speech, e.g. gender, age, etc. In this paper, we address the challenge posed by a subtask of voice profiling - reconstructing someone's face from their voice. The task is designed to answer the question: given an audio clip spoken…
The following topics are dealt with: learning (artificial intelligence); neural nets; speech recognition; feature extraction; convolutional neural nets; acoustic signal processing; speech processing; optimisation; speaker recognition; recurrent neural nets.
In this paper we present a transformation to convert time signals into a randomized low-dimensional vectors such that the inner product between these new features provides information about the similarity of the signals. We show that the described inner product approximates a cross-correlation based…
We present a conceptually plausible approach for text-independent speaker verification (TISV) which treats speech recordings as a collection of segments providing incremental evidence. This approach, called corrective learning, gradually improves an initial prediction of speaker identity based on in…
State of the art acoustic scene classification techniques often employ features of large dimensionality, which are then used to train and perform inferences with kernel machines such as Support Vector Machines. However, the complexity of computing the non-linear kernel matrix for these methods incre…
In this paper, we focus on the problem of content-based retrieval for audio, which aims to retrieve all semantically similar audio recordings for a given audio clip query. This problem is similar to the problem of query by example of audio, which aims to retrieve media samples from a database, which…
The largest source of sound events is web videos. Most videos lack sound event labels at segment level, however, a significant number of them do respond to text queries, from a match found using metadata by search engines. In this paper we explore the extent to which a search query can be used as th…
Voice impersonation is not the same as voice transformation, although the latter is an essential element of it. In voice impersonation, the resultant voice must convincingly convey the impression of having been naturally produced by the target speaker, mimicking not only the pitch and other perceiva…
In this paper we describe approaches for discovering acoustic concepts and relations in text. The first major goal is to be able to identify text phrases which contain a notion of audibility and can be termed as a sound or an acoustic concept. We also propose a method to define an acoustic scene thr…
A critically important component of most signal processing procedures is that of computing the distance between signals. In multiparty processing applications where these signals belong to different parties, this introduces privacy challenges. The signals may themselves be private, and the parties t…
This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. However, few existing algorithms can effectively achieve this c…
In this paper, we propose a new supervised monaural source separation based on autoencoders. We employ the autoencoder for the dictionary training such that the nonlinear network can encode the target source with high expressiveness. The dictionary is trained by each target source without the mixtur…
In a speech signal, Voice Onset Time (VOT) is the period between the release of a plosive and the onset of vocal cord vibrations in the production of the following sound. Voice Offset Time (VOFT), on the other hand, is the period between the end of a voiced sound and the release of the following plo…
We introduce an unsupervised optimization method for optimal fusion of multiple classifiers in retrieval problems. The method is based on a ranking loss called the “clarity” index, which does not depend on the label of the test instances. The technique optimizes the weights with which individual cla…
Most state-of-the-art action feature extractors involve differential operators, which act as highpass filters and tend to attenuate low frequency action information. This attenuation introduces bias to the resulting features and generates ill-conditioned feature matrices. The Gaussian Pyramid has be…
This paper investigates a new privacy-preserving paradigm for the task of Query-by-Example Speech Search using Secure Binary Embeddings, a hashing method that converts vector data to bit strings through a combination of random projections followed by banded quantization. The proposed method allows p…
Large-scale distributed learning plays an ever-more increasing role in modern computing. However, whether using a compute cluster with thousands of nodes, or a single multi-GPU machine, the most significant bottleneck is that of communication. In this work, we explore the effects of applying quantiz…