arXiv subjects

Anurag Kumar

Publications and source records attributed to Anurag Kumar.

At least 37 records · Page 2Linked to original sources

arXiv2024

Language-Guided Joint Audio-Visual Editing via One-Shot Adaptation

In this paper, we introduce a novel task called language-guided joint audio-visual editing. Given an audio and image pair of a sounding event, this task aims at generating new audio-visual content by editing the given sounding event conditioned on the language guidance. For instance, we can alter the background environment of a sounding object while keeping its appearance unchanged, or we can add new sounds contextualized to the visual content. To address this task, we propose a new diffusion-based framework for joint audio-visual editing and introduce two key ideas. Firstly, we propose a one-shot adaptation approach to tailor generative diffusion models for audio-visual content editing. With as few as one audio-visual sample, we jointly transfer the audio and vision diffusion models to the target domain. After fine-tuning, our model enables consistent generation of this audio-visual sample. Secondly, we introduce a cross-modal semantic enhancement approach. We observe that when using language as content editing guidance, the vision branch may overlook editing requirements. This phenomenon, termed catastrophic neglect, hampers audio-visual alignment during content editing. We therefore enhance semantic consistency between language and vision to mitigate this issue. Extensive experiments validate the effectiveness of our method in language-based audio-visual editing and highlight its superiority over several baseline approaches. We recommend that readers visit our project page for more details: https://liangsusan-git.github.io/project/avedit/.

cs.CV↗

arXiv2024

Scaling Concept With Text-Guided Diffusion Models

Text-guided diffusion models have revolutionized generative tasks by producing high-fidelity content from text descriptions. They have also enabled an editing paradigm where concepts can be replaced through text conditioning (e.g., a dog to a tiger). In this work, we explore a novel approach: instead of replacing a concept, can we enhance or suppress the concept itself? Through an empirical study, we identify a trend where concepts can be decomposed in text-guided diffusion models. Leveraging this insight, we introduce ScalingConcept, a simple yet effective method to scale decomposed concepts up or down in real input without introducing new elements. To systematically evaluate our approach, we present the WeakConcept-10 dataset, where concepts are imperfect and need to be enhanced. More importantly, ScalingConcept enables a variety of novel zero-shot applications across image and audio domains, including tasks such as canonical pose generation and generative sound highlighting or removal.

cs.CV↗

arXiv2024

Using RLHF to align speech enhancement approaches to mean-opinion quality scores

Objective speech quality measures are typically used to assess speech enhancement algorithms, but it has been shown that they are sub-optimal as learning objectives because they do not always align well with human subjective ratings. This misalignment often results in noticeable distortions and artifacts that cause speech enhancement to be ineffective. To address these issues, we propose a reinforcement learning from human feedback (RLHF) framework to fine-tune an existing speech enhancement approach by optimizing performance using a mean-opinion score (MOS)-based reward model. Our results show that the RLHF-finetuned model has the best performance across different benchmarks for both objective and MOS-based speech quality assessment metrics on the Voicebank+DEMAND dataset. Through ablation studies, we show that both policy gradient loss and supervised MSE loss are important for balanced optimization across the different metrics.

eess.AS↗

arXiv2024

High Fidelity Text-Guided Music Editing via Single-Stage Flow Matching

We introduce MelodyFlow, an efficient text-controllable high-fidelity music generation and editing model. It operates on continuous latent representations from a low frame rate 48 kHz stereo variational auto encoder codec. Based on a diffusion transformer architecture trained on a flow-matching objective the model can edit diverse high quality stereo samples of variable duration, with simple text descriptions. We adapt the ReNoise latent inversion method to flow matching and compare it with the original implementation and naive denoising diffusion implicit model (DDIM) inversion on a variety of music editing prompts. Our results indicate that our latent inversion outperforms both ReNoise and DDIM for zero-shot test-time text-guided editing on several objective metrics. Subjective evaluations exhibit a substantial improvement over previous state of the art for music editing. Code and model weights will be publicly made available. Samples are available at https://melodyflow.github.io.

eess.AS↗

arXiv2024

High-Quality Visually-Guided Sound Separation from Diverse Categories

We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-based regression problem, achieving significant progress. However, they face limitations in capturing the complex data distribution required for high-quality separation of sounds from diverse categories. In contrast, DAVIS leverages a generative diffusion model and a Separation U-Net to synthesize separated sounds directly from Gaussian noise, conditioned on both the audio mixture and the visual information. With its generative objective, DAVIS is better suited to achieving the goal of high-quality sound separation across diverse sound categories. We compare DAVIS to existing state-of-the-art discriminative audio-visual separation methods on the AVE and MUSIC datasets, and results show that DAVIS outperforms other methods in separation quality, demonstrating the advantages of our framework for tackling the audio-visual source separation task.

cs.CV↗

arXiv2024

Improved direction of arrival estimations with a wearable microphone array for dynamic environments by reliability weighting

Direction-of-arrival estimation of multiple speakers in a room is an important task for a wide range of applications. In particular, challenging environments with moving speakers, reverberation and noise, lead to significant performance degradation for current methods. With the aim of better understanding factors affecting performance and improving current methods, in this paper multi-speaker direction-of-arrival (DOA) estimation is investigated using a modified version of the local space domain distance (LSDD) algorithm in a noisy, dynamic and reverberant environment employing a wearable microphone array. This study utilizes the recently published EasyCom speech dataset, recorded using a wearable microphone array mounted on eyeglasses. While the original LSDD algorithm demonstrates strong performance in static environments, its efficacy significantly diminishes in the dynamic settings of the EasyCom dataset. Several enhancements to the LSDD algorithm are developed following a comprehensive performance and system analysis, which enable improved DOA estimation under these challenging conditions. These improvements include incorporating a weighted reliability approach and introducing a new quality measure that reliably identifies the more accurate DOA estimates, thereby enhancing both the robustness and accuracy of the algorithm in challenging environments.

eess.AS↗

arXiv2024

Non-verbal Hands-free Control for Smart Glasses using Teeth Clicks

Smart glasses are emerging as a popular wearable computing platform potentially revolutionizing the next generation of human-computer interaction. The widespread adoption of smart glasses has created a pressing need for discreet and hands-free control methods. Traditional input techniques, such as voice commands or tactile gestures, can be intrusive and non-discreet. Additionally, voice-based control may not function well in noisy acoustic conditions. We propose a novel, discreet, non-verbal, and non-tactile approach to controlling smart glasses through subtle vibrations on the skin induced by teeth clicking. We demonstrate that these vibrations can be sensed by accelerometers embedded in the glasses with a low-footprint predictive model. Our proposed method, called STEALTHsense, utilizes a temporal broadcasting-based neural network architecture with just 88K trainable parameters and 7.14M Multiply and Accumulate (MMAC) per inference unit. We benchmark our proposed STEALTHsense against state-of-the-art deep learning approaches and traditional low-footprint machine learning approaches. We conducted a study across 21 participants to collect representative samples for two distinct teeth-clicking patterns and many non-patterns for robust training of STEALTHsense, achieving an average cross-person accuracy of 0.93. Field testing confirmed its effectiveness, even in noisy conditions, underscoring STEALTHsense's potential for real-world applications, offering a promising solution for smart glasses interaction.

cs.HC↗

arXiv2024

Utility Optimal Scheduling with a Slow Time-Scale Index-Bias for Achieving Rate Guarantees in Cellular Networks

One of the requirements of network slicing in 5G networks is RAN (radio access network) scheduling with rate guarantees. We study a three-time-scale algorithm for maximum sum utility scheduling, with minimum rate constraints. As usual, the scheduler computes an index for each UE in each slot, and schedules the UE with the maximum index. This is at the fastest, natural time-scale of channel fading. The next time-scale is of the exponentially weighted moving average (EWMA) rate update. The slowest time scale in our algorithm is an "index-bias" update by a stochastic approximation algorithm, with a step-size smaller than the EWMA. The index-biases are related to Lagrange multipliers, and bias the slot indices of the UEs with rate guarantees, promoting their more frequent scheduling. We obtain a pair of coupled ordinary differential equations (o.d.e.) such that the unique stable points of the two o.d.e.s are the primal and dual solutions of the constrained utility optimization problem. The UE rate and index-bias iterations track the asymptotic behaviour of the o.d.e. system for small step-sizes of the two slower time-scale iterations. Simulations show that, by running the index-bias iteration at a slower time-scale than the EWMA iteration and using the EWMA throughput itself in the index-bias update, the UE rates stabilize close to the optimum operating point on the rate region boundary, and the index-biases have small fluctuations around the optimum Lagrange multipliers. We compare our results with a prior two-time-scale algorithm and show improved performance.

cs.NI↗

arXiv2024

Few Shot Class Incremental Learning using Vision-Language models

Recent advancements in deep learning have demonstrated remarkable performance comparable to human capabilities across various supervised computer vision tasks. However, the prevalent assumption of having an extensive pool of training data encompassing all classes prior to model training often diverges from real-world scenarios, where limited data availability for novel classes is the norm. The challenge emerges in seamlessly integrating new classes with few samples into the training data, demanding the model to adeptly accommodate these additions without compromising its performance on base classes. To address this exigency, the research community has introduced several solutions under the realm of few-shot class incremental learning (FSCIL). In this study, we introduce an innovative FSCIL framework that utilizes language regularizer and subspace regularizer. During base training, the language regularizer helps incorporate semantic information extracted from a Vision-Language model. The subspace regularizer helps in facilitating the model's acquisition of nuanced connections between image and text semantics inherent to base classes during incremental training. Our proposed framework not only empowers the model to embrace novel classes with limited data, but also ensures the preservation of performance on base classes. To substantiate the efficacy of our approach, we conduct comprehensive experiments on three distinct FSCIL benchmarks, where our framework attains state-of-the-art performance.

cs.CV↗

arXiv2024

Spherical World-Locking for Audio-Visual Localization in Egocentric Videos

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.

cs.CV↗

arXiv2024

AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling

Adding visual cues to audio-based speech separation can improve separation performance. This paper introduces AV-CrossNet, an audiovisual (AV) system for speech enhancement, target speaker extraction, and multi-talker speaker separation. AV-CrossNet is extended from the CrossNet architecture, which is a recently proposed network that performs complex spectral mapping for speech separation by leveraging global attention and positional encoding. To effectively utilize visual cues, the proposed system incorporates pre-extracted visual embeddings and employs a visual encoder comprising temporal convolutional layers. Audio and visual features are fused in an early fusion layer before feeding to AV-CrossNet blocks. We evaluate AV-CrossNet on multiple datasets, including LRS, VoxCeleb, and COG-MHEAR challenge. Evaluation results demonstrate that AV-CrossNet advances the state-of-the-art performance in all audiovisual tasks, even on untrained and mismatched datasets.

eess.AS↗

arXiv2024

URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement

The last decade has witnessed significant advancements in deep learning-based speech enhancement (SE). However, most existing SE research has limitations on the coverage of SE sub-tasks, data diversity and amount, and evaluation metrics. To fill this gap and promote research toward universal SE, we establish a new SE challenge, named URGENT, to focus on the universality, robustness, and generalizability of SE. We aim to extend the SE definition to cover different sub-tasks to explore the limits of SE models, starting from denoising, dereverberation, bandwidth extension, and declipping. A novel framework is proposed to unify all these sub-tasks in a single model, allowing the use of all existing SE approaches. We collected public speech and noise data from different domains to construct diverse evaluation data. Finally, we discuss the insights gained from our preliminary baseline experiments based on both generative and discriminative SE methods with 12 curated metrics.

eess.AS↗

arXiv2024

Cross-Talk Reduction

While far-field multi-talker mixtures are recorded, each speaker can wear a close-talk microphone so that close-talk mixtures can be recorded at the same time. Although each close-talk mixture has a high signal-to-noise ratio (SNR) of the wearer, it has a very limited range of applications, as it also contains significant cross-talk speech by other speakers and is not clean enough. In this context, we propose a novel task named cross-talk reduction (CTR) which aims at reducing cross-talk speech, and a novel solution named CTRnet which is based on unsupervised or weakly-supervised neural speech separation. In unsupervised CTRnet, close-talk and far-field mixtures are stacked as input for a DNN to estimate the close-talk speech of each speaker. It is trained in an unsupervised, discriminative way such that the DNN estimate for each speaker can be linearly filtered to cancel out the speaker's cross-talk speech captured at other microphones. In weakly-supervised CTRnet, we assume the availability of each speaker's activity timestamps during training, and leverage them to improve the training of unsupervised CTRnet. Evaluation results on a simulated two-speaker CTR task and on a real-recorded conversational speech separation and recognition task show the effectiveness and potential of CTRnet.

eess.AS↗

arXiv2024

Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark

We present a new dataset called Real Acoustic Fields (RAF) that captures real acoustic room data from multiple modalities. The dataset includes high-quality and densely captured room impulse response data paired with multi-view images, and precise 6DoF pose tracking data for sound emitters and listeners in the rooms. We used this dataset to evaluate existing methods for novel-view acoustic synthesis and impulse response generation which previously relied on synthetic data. In our evaluation, we thoroughly assessed existing audio and audio-visual models against multiple criteria and proposed settings to enhance their performance on real-world data. We also conducted experiments to investigate the impact of incorporating visual data (i.e., images and depth) into neural acoustic field models. Additionally, we demonstrated the effectiveness of a simple sim2real approach, where a model is pre-trained with simulated data and fine-tuned with sparse real-world data, resulting in significant improvements in the few-shot learning approach. RAF is the first dataset to provide densely captured room acoustic data, making it an ideal resource for researchers working on audio and audio-visual neural acoustic field modeling techniques. Demos and datasets are available on our project page: https://facebookresearch.github.io/real-acoustic-fields/

cs.SD↗

arXiv2024

A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement

Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others. While the features are undeniably useful in speech recognition and associated tasks, their utility in speech enhancement systems is yet to be firmly established, and perhaps not properly understood. In this paper, we investigate the uses of SSL representations for single-channel speech enhancement in challenging conditions and find that they add very little value for the enhancement task. Our constraints are designed around on-device real-time speech enhancement -- model is causal, the compute footprint is small. Additionally, we focus on low SNR conditions where such models struggle to provide good enhancement. In order to systematically examine how SSL representations impact performance of such enhancement models, we propose a variety of techniques to utilize these embeddings which include different forms of knowledge-distillation and pre-training.

eess.AS↗

arXiv2024

Ambisonics Networks -- The Effect Of Radial Functions Regularization

Ambisonics, a popular format of spatial audio, is the spherical harmonic (SH) representation of the plane wave density function of a sound field. Many algorithms operate in the SH domain and utilize the Ambisonics as their input signal. The process of encoding Ambisonics from a spherical microphone array involves dividing by the radial functions, which may amplify noise at low frequencies. This can be overcome by regularization, with the downside of introducing errors to the Ambisonics encoding. This paper aims to investigate the impact of different ways of regularization on Deep Neural Network (DNN) training and performance. Ideally, these networks should be robust to the way of regularization. Simulated data of a single speaker in a room and experimental data from the LOCATA challenge were used to evaluate this robustness on an example algorithm of speaker localization based on the direct-path dominance (DPD) test. Results show that performance may be sensitive to the way of regularization, and an informed approach is proposed and investigated, highlighting the importance of regularization information.

eess.AS↗

arXiv2023

TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch

TorchAudio is an open-source audio and speech processing library built for PyTorch. It aims to accelerate the research and development of audio and speech technologies by providing well-designed, easy-to-use, and performant PyTorch components. Its contributors routinely engage with users to understand their needs and fulfill them by developing impactful features. Here, we survey TorchAudio's development principles and contents and highlight key features we include in its latest version (2.1): self-supervised learning pre-trained pipelines and training recipes, high-performance CTC decoders, speech recognition models and training recipes, advanced media I/O capabilities, and tools for performing forced alignment, multi-channel speech enhancement, and reference-less speech assessment. For a selection of these features, through empirical studies, we demonstrate their efficacy and show that they achieve competitive or state-of-the-art performance.

eess.AS↗

arXiv2023

AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis

Can machines recording an audio-visual scene produce realistic, matching audio-visual experiences at novel positions and novel view directions? We answer it by studying a new task -- real-world audio-visual scene synthesis -- and a first-of-its-kind NeRF-based approach for multimodal learning. Concretely, given a video recording of an audio-visual scene, the task is to synthesize new videos with spatial audios along arbitrary novel camera trajectories in that scene. We propose an acoustic-aware audio generation module that integrates prior knowledge of audio propagation into NeRF, in which we implicitly associate audio generation with the 3D geometry and material properties of a visual environment. Furthermore, we present a coordinate transformation module that expresses a view direction relative to the sound source, enabling the model to learn sound source-centric acoustic fields. To facilitate the study of this new task, we collect a high-quality Real-World Audio-Visual Scene (RWAVS) dataset. We demonstrate the advantages of our method on this real-world dataset and the simulation-based SoundSpaces dataset.

cs.CV↗