Anurag Kumar

Heeseung Yun, Ruohan Gao, Ishwarya Ananthabhotla et al.

Egocentric videos provide comprehensive contexts for user and scene understanding, spanning multisensory perception to behavioral interaction. We propose Spherical World-Locking (SWL) as a general framework for egocentric scene representation, which implicitly transforms multisensory streams with respect to measurements of head orientation. Compared to conventional head-locked egocentric representations with a 2D planar field-of-view, SWL effectively offsets challenges posed by self-motion, allowing for improved spatial synchronization between input modalities. Using a set of multisensory embeddings on a worldlocked sphere, we design a unified encoder-decoder transformer architecture that preserves the spherical structure of the scene representation, without requiring expensive projections between image and world coordinate systems. We evaluate the effectiveness of the proposed framework on multiple benchmark tasks for egocentric video understanding, including audio-visual active speaker localization, auditory spherical source localization, and behavior anticipation in everyday activities.

Xiulong Liu, Anurag Kumar, Paul Calamia et al.

In mixed reality applications, a realistic acoustic experience in spatial environments is as crucial as the visual experience for achieving true immersion. Despite recent advances in neural approaches for Room Impulse Response (RIR) estimation, most existing methods are limited to the single environment on which they are trained, lacking the ability to generalize to new rooms with different geometries and surface materials. We aim to develop a unified model capable of reconstructing the spatial acoustic experience of any environment with minimum additional measurements. To this end, we present xRIR, a framework for cross-room RIR prediction. The core of our generalizable approach lies in combining a geometric feature extractor, which captures spatial context from panorama depth images, with a RIR encoder that extracts detailed acoustic features from only a few reference RIR samples. To evaluate our method, we introduce ACOUSTICROOMS, a new dataset featuring high-fidelity simulation of over 300,000 RIRs from 260 rooms. Experiments show that our method strongly outperforms a series of baselines. Furthermore, we successfully perform sim-to-real transfer by evaluating our model on four real-world environments, demonstrating the generalizability of our approach and the realism of our dataset.

Chao Huang, Ruohan Gao, J. M. F. Tsang et al.

Recent years have seen a significant increase in video content creation and consumption. Crafting engaging content requires the careful curation of both visual and audio elements. While visual cue curation, through techniques like optimal viewpoint selection or post-editing, has been central to media production, its natural counterpart, audio, has not undergone equivalent advancements. This often results in a disconnect between visual and acoustic saliency. To bridge this gap, we introduce a novel task: visually-guided acoustic highlighting, which aims to transform audio to deliver appropriate highlighting effects guided by the accompanying video, ultimately creating a more harmonious audio-visual experience. We propose a flexible, transformer-based multimodal framework to solve this task. To train our model, we also introduce a new dataset -- the muddy mix dataset, leveraging the meticulous audio and video crafting found in movies, which provides a form of free supervision. We develop a pseudo-data generation process to simulate poorly mixed audio, mimicking real-world scenarios through a three-step process -- separation, adjustment, and remixing. Our approach consistently outperforms several baselines in both quantitative and subjective evaluation. We also systematically study the impact of different types of contextual guidance and difficulty levels of the dataset. Our project page is here: https://wikichao.github.io/VisAH/.

Joanna Hong, Sanjeel Parekh, Honglie Chen et al.

Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions frequently lead to improvements in performance and may even be critical in certain cases, they come with several constraints such as increased sensory requirements, computational cost, and modality synchronization, to mention a few. These challenges constrain the direct uses of these multimodal solutions in real-world applications. In this work, we develop approaches where the learning happens with all available modalities but the deployment or inference is done with just one or reduced modalities. To do so, we propose a Multimodal Training and Unimodal Deployment (MUTUD) framework which includes a Temporally Aligned Modality feature Estimation (TAME) module that can estimate information from missing modality using modalities present during inference. This innovative approach facilitates the integration of information across different modalities, enhancing the overall inference process by leveraging the strengths of each modality to compensate for the absence of certain modalities during inference. We apply MUTUD to various audiovisual speech tasks and show that it can reduce the performance gap between the multimodal and corresponding unimodal models to a considerable extent. MUTUD can achieve this while reducing the model size and compute compared to multimodal models, in some cases by almost 80%.

Efthymios Tzinis, Yossi Adi, Vamsi Krishna Ithapu et al.

We present RemixIT, a simple yet effective self-supervised method for training speech enhancement without the need of a single isolated in-domain speech nor a noise waveform. Our approach overcomes limitations of previous methods which make them dependent on clean in-domain target signals and thus, sensitive to any domain mismatch between train and test samples. RemixIT is based on a continuous self-training scheme in which a pre-trained teacher model on out-of-domain data infers estimated pseudo-target signals for in-domain mixtures. Then, by permuting the estimated clean and noise signals and remixing them together, we generate a new set of bootstrapped mixtures and corresponding pseudo-targets which are used to train the student network. Vice-versa, the teacher periodically refines its estimates using the updated parameters of the latest student models. Experimental results on multiple speech enhancement datasets and tasks not only show the superiority of our method over prior approaches but also showcase that RemixIT can be combined with any separation model as well as be applied towards any semi-supervised and unsupervised domain adaptation task. Our analysis, paired with empirical evidence, sheds light on the inside functioning of our self-training scheme wherein the student model keeps obtaining better performance while observing severely degraded pseudo-targets.

A Kishore Kumar, Shefali Waldekar, Goutam Saha et al.

This report describes the speaker diarization system developed by the ABSP Laboratory team for the third DIHARD speech diarization challenge. Our primary contribution is to develop acoustic domain identification (ADI) system for speaker diarization. We investigate speaker embeddings based ADI system. We apply a domain-dependent threshold for agglomerative hierarchical clustering. Besides, we optimize the parameters for PCA-based dimensionality reduction in a domain-dependent way. Our method of integrating domain-based processing schemes in the baseline system of the challenge achieved a relative improvement of $9.63\%$ and $10.64\%$ in DER for core and full conditions, respectively, for Track 1 of the DIHARD III evaluation set.

Anastasia Kuznetsova, Anurag Kumar, Francis M. Tyers

The Automated Speech Recognition (ASR) task has been a challenging domain especially for low data scenarios with few audio examples. This is the main problem in training ASR systems on the data from low-resource or marginalized languages. In this paper we present an approach to mitigate the lack of training data by employing Automated Curriculum Learning in combination with an adversarial bandit approach inspired by Reinforcement learning. The goal of the approach is to optimize the training sequence of mini-batches ranked by the level of difficulty and compare the ASR performance metrics against the random training sequence and discrete curriculum. We test our approach on a truly low-resource language and show that the bandit framework has a good improvement over the baseline transfer-learning model.

A Kishore Kumar, Shefali Waldekar, Goutam Saha et al.

This report presents the system developed by the ABSP Laboratory team for the third DIHARD speech diarization challenge. Our main contribution in this work is to develop a simple and efficient solution for acoustic domain dependent speech diarization. We explore speaker embeddings for \emph{acoustic domain identification} (ADI) task. Our study reveals that i-vector based method achieves considerably better performance than x-vector based approach in the third DIHARD challenge dataset. Next, we integrate the ADI module with the diarization framework. The performance substantially improved over that of the baseline when we optimized the thresholds for agglomerative hierarchical clustering and the parameters for dimensionality reduction during scoring for individual acoustic domains. We achieved a relative improvement of $9.63\%$ and $10.64\%$ in DER for core and full conditions, respectively, for Track 1 of the DIHARD III evaluation set.

Anurag Kumar, Bhiksha Raj

In this paper we present an unsupervised method to learn the weights with which the scores of multiple classifiers must be combined in classifier fusion settings. We also introduce a novel metric for ranking instances based on an index which depends upon the rank of weighted scores of test points among the weighted scores of training points. We show that the optimized index can be used for computing measures such as average precision. Unlike most classifier fusion methods where a single weight is learned to weigh all examples our method learns instance-specific weights. The problem is formulated as learning the weight which maximizes a clarity index; subsequently the index itself and the learned weights both are used separately to rank all the test points. Our method gives an unsupervised method of optimizing performance on actual test data, unlike the well known stacking-based methods where optimization is done over a labeled training set. Moreover, we show that our method is tolerant to noisy classifiers and can be used for selecting N-best classifiers.