Searcharxiv⌕ Search

arXiv subjects

Vipul Arora

Publications and source records attributed to Vipul Arora.

At least 19 recordsLinked to original sources
arXiv2026

Sector-Resolved Flow Sampling for Topologically Frozen Lattice Gauge Theories

Topological fluctuations are essential to nonperturbative gauge theories but become increasingly difficult to sample toward the continuum limit, where Markov chains can freeze in sectors of fixed topological charge. We introduce a generative sampler, a mixture of sector-resolved samplers (MSRS) that explicitly resolves these sectors and exploits a key advantage of generative models, the ability to directly evaluate the domain-restricted partition function and thereby determine the relative weights of disconnected sectors. We train a generative model in a reference topological sector combined with a bijective topological shift that deterministically maps its samples to other sectors. We demonstrate the method in two-dimensional compact U (1) lattice gauge theory, where it reproduces the topological-charge distribution and yields an unbiased susceptibility in a regime where hybrid Monte Carlo is frozen and overrelaxation gives inaccurate estimates. Our approach also outperforms existing flow-based samplers by orders of magnitude. These results demonstrate that explicit sector resolution provides a promising route to overcoming topological barriers in lattice gauge theory.

hep-lat↗
arXiv2026

Probing Criticality Using GMM-Based Potentials

Spin models with a given symmetry are easier to sample than scalar theories with the same symmetry on a lattice, as the constrained nature of spin variables enables cheap heat-bath updates. However, this constraint suppresses radial fluctuations, and consequently, spin models cannot be used to study the phenomena of spontaneous symmetry breaking, such as the Higgs phenomenon. To address this, we propose a class of scalar potentials based on Gaussian Mixture Models (GMMs) that are as easy to sample as spin models with a given symmetry. These potentials can be designed to belong to the same universality class as the theory of interest, thereby reproducing its critical properties while enabling efficient sampling. We construct such models for global $\mathbb{Z}_2$ symmetry, $U(1)$ gauge symmetry, and disordered systems. We also verify by numerical experiment that the case of $\mathbb{Z}_2$ symmetry in two dimensions lies in the two-dimensional Ising universality class.

hep-lat↗
arXiv2026

Weakly Supervised Tabla Stroke Transcription via an Adaptive Dynamic Rhythm Language Model (ADRM)

Tabla Stroke Transcription (TST) is central to the analysis of rhythmic structure in Hindustani music, yet it remains challenging due to complex and dynamic rhythmic organization and the scarcity of strongly annotated data. Existing approaches largely rely on fully supervised learning with onset-level annotations, which are costly and impractical at scale. This work addresses TST in a weakly supervised setting, using only symbolic stroke sequences without temporal alignment of onsets. We propose a framework that combines a Connectionist Temporal Classification (CTC)-based acoustic model with a sequence-level rhythmic language model for rescoring, similar to that used in automatic speech recognition. The acoustic model produces a decoding lattice, which is refined using an Adaptive Dynamic Rhythm Language Model (ADRM) that combines $t\bar{a}la$-conditioned symbolic rhythmic regularities with local stroke dynamics. Moreover, we release a new performance-recorded tabla dataset, named \emph{Tabla Improvisation Dataset}, along with a complementary synthetic dataset for sequence-level weakly supervised TST. Experiments demonstrate consistent and substantial reductions in stroke error rates with ADRM compared to those with acoustic-only decoding, confirming the benefit of incorporating symbolic rhythmic regularities during lattice rescoring for accurate transcription.

eess.AS↗
arXiv2026

$TCP_\alpha$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval

Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions. Consequently, users lack a reliable signal for deciding when a prediction can be trusted. Post-hoc confidence estimation addresses this by training a lightweight auxiliary head over a frozen classifier. Existing targets, however, suffer from inherent ambiguity: they assign overlapping confidence values to correct and incorrect predictions, while errors near the decision boundary receive confidence scores indistinguishable from correct predictions. In this work, we propose $TCP_\alpha$, a novel confidence target that resolves these limitations by introducing a margin-controlled penalty for misclassified samples. We prove that $TCP_\alpha$ guarantees complete separation between the target values of correct and incorrect predictions, with a separation margin that is independent of the number of classes and increases monotonically with the penalty parameter. Since accurate classifiers naturally produce very few errors, learning these targets results in a severely imbalanced regression problem. We therefore present a systematic study of training strategies for learning under this imbalance and identify an effective training configuration through extensive ablation studies. We evaluate the proposed approach on r\=aga identification, investigate its robustness under domain shift, and further validate it on frame-wise ornamentation detection without modifying the selected configuration. Across all settings, $TCP_\alpha$ consistently outperforms existing confidence targets for failure prediction. Rejecting only the least-confident 8\% of predictions improves the base model's macro-F1 from 0.89 to 0.98, while fine-tuning the confidence head with only 5\% labeled samples from a new corpus effectively restores performance under domain shift.

eess.AS↗
arXiv2026

wav2tok 2.0: Scalable Audio Tokenization Maintaining Explicit Pairwise Token Alignment for Efficient Audio Retrieval

Learning discrete speech representations that preserve similarity across variable-length utterances is central to query-by-example spoken term detection (QbE-STD). While wav2tok introduced CTC-based sequence alignment to enforce token consistency, its tightly coupled clustering and alignment training recipe limits scalability. We propose wav2tok 2.0, a scalable alignment-aware speech tokenizer built on the BEST-STD backbone. wav2tok 2.0 employs staged training, first learning discriminative, speaker-invariant representations via contrastive learning and vector quantization, and then enforcing pairwise token consistency using a CTC alignment loss and a novel DTW-aligned framewise prediction objective with adaptive weighting. Experiments show that wav2tok 2.0 consistently outperforms BEST-STD and general-purpose tokenizers on QbE-STD while remaining efficient and scalable.

cs.SD↗
arXiv2026

PairAlign: A Framework for Autoregressive Tokenization via Self-Alignment with Applications to Audio Tokenization

Modern learning systems represent perceptual signals with continuous vectors, but comparison, retrieval, memory, alignment, and reasoning are often symbolic. In language, tokens provide this interface; for speech and audio, it must be learned. Existing audio tokenizers rely on local quantization, clustering, or reconstruction, leaving sequence consistency, compactness, length, termination, and edit geometry only indirectly controlled. We introduce PairAlign, a framework for compact audio tokenization through autoregressive self-alignment. An encoder maps speech to a continuous condition, and an autoregressive decoder emits tokens from BOS to EOS. Given two content-preserving views, PairAlign derives a canonical anchor target and trains both views to predict it, with unrelated in-batch targets as competing sequences. It first learns an autoregressive bridge from VQ targets and then transitions to EMA-teacher self-alignment with grounding and anti-collapse controls. On 3 s speech, PairAlign produces shorter, non-degenerate sequences while retaining ordered paired-view consistency. On the TIMIT retrieval archive, it operates at 8.28 tokens/s, reducing archive token count by 70.65% and the edit-distance work proxy by 91.87% relative to Stage I. Positive-negative probes show strong separation across phone-disjoint, trigram-disjoint, and temporally rearranged negatives, while rate-controlled post-hoc BPE does not recover the same compactness-consistency operating point. These results expose a rate-granularity trade-off: PairAlign does not uniformly outperform denser tokenizers on every local metric, but provides a lower-rate symbolic interface preserving ordered and relational structure. Conceptually, PairAlign follows JEPA-style predictive learning by predicting an abstract target rather than reconstructing the input; here, the target is a learned variable-length symbolic sequence.

cs.LG↗
arXiv2026

Testing Sparse Functions over the Reals

Over the last three decades, function testing has been extensively studied over Boolean, finite fields, and discrete settings. However, to encode the real-world applications more succinctly, function testing over the reals (where the domain and range, both are reals) is of prime importance. Recently, there have been some works in the direction of testing for algebraic representations of such functions: the work by Fleming and Yoshida (ITCS 20), Arora, Kelman, and Meir (SOSA 25) on linearity testing and the work of Arora, Bhattacharyya, Fleming, Kelman, and Yoshida (SODA 23) for testing low-degree polynomials. Our work follows the same avenue, wherein we study three well-studied sparse representations of functions, over the reals, namely (i) $k$-linearity, (ii) $k$-sparse polynomials, and (iii) $k$-junta. In this setting, given approximate query access to some $f:\mathbb{R}^n \rightarrow \mathbb{R}$, we want to decide if the function satisfies some property of interest, or if it is far from all functions that satisfy the property. Here, the distance is measured in the $\ell_1$-metric, under the assumption that we are drawing samples from the Standard Gaussian distribution. We present efficient testers and $\Omega(k)$ lower bounds for testing each of these three properties.

cs.DS↗
arXiv2026

Automatic Detection and Analysis of Singing Mistakes for Music Pedagogy

The advancement of machine learning in audio analysis has opened new possibilities for technology-enhanced music education. This paper introduces a framework for automatic singing mistake detection in the context of music pedagogy, supported by a newly curated dataset. The dataset comprises synchronized teacher learner vocal recordings, with annotations marking different types of mistakes made by learners. Using this dataset, we develop different deep learning models for mistake detection and benchmark them. To compare the efficacy of mistake detection systems, a new evaluation methodology is proposed. Experiments indicate that the proposed learning-based methods are superior to rule-based methods. A systematic study of errors and a cross-teacher study reveal insights into music pedagogy that can be utilised for various music applications. This work sets out new directions of research in music pedagogy. The codes and dataset are publicly available.

eess.AS↗
arXiv2026

Learning to Discover: A Generalized Framework for Raga Identification without Forgetting

Raga identification in Indian Art Music (IAM) remains challenging due to the presence of numerous rarely performed Ragas that are not represented in available training datasets. Traditional classification models struggle in this setting, as they assume a closed set of known categories and therefore fail to recognise or meaningfully group previously unseen Ragas. Recent works have tried categorizing unseen Ragas, but they run into a problem of catastrophic forgetting, where the knowledge of previously seen Ragas is diminished. To address this problem, we adopt a unified learning framework that leverages both labeled and unlabeled audio, enabling the model to discover coherent categories corresponding to the unseen Ragas, while retaining the knowledge of previously known ones. We test our model on benchmark Raga Identification datasets and demonstrate its performance in categorizing previously seen, unseen, and all Raga classes. The proposed approach surpasses the previous NCD-based pipeline even in discovering the unseen Raga categories, offering new insights into representation learning for IAM tasks.

eess.AS↗
arXiv2026

TORRCH: Tomographic reconstruction of the reionization of cosmic hydrogen with Ly${\alpha}$ emitters and non-Ly${\alpha}$-selected galaxies

Tomographic reconstruction of reionization is a long-sought goal. It would move the field beyond global summary statistics, such as the volume-averaged ionised fraction, to direct, field-level constraints on the ionization topology. With this in mind, we present TORRCH (TOmographic Reconstruction of the Reionization of Cosmic Hydrogen), a deep-learning framework that reconstructs the neutral-hydrogen fraction field during the epoch of reionization from the spatial distributions of Ly$\alpha$ emitters (LAEs) and non-Ly$\alpha$-selected galaxies (NLSGs) at luminosity limits comparable to current surveys. Using hydrodynamical simulations post-processed with radiative transfer, we train a deterministic 3D U-Net on mock surveys spanning diverse reionization scenarios and predict the neutral-fraction field. We find that TORRCH recovers the large-scale ionization morphology from synthetic data comparable to current surveys with high fidelity, and reproduces both the one-point distribution and the 2D power spectrum of projected neutral fractions. The predicted galaxy-IGM cross-correlation is also captured well, including the expected small-scale anti-correlation and its decline towards zero at large separations. Reconstruction quality depends on tracer completeness, with deep joint LAE+NLSG samples yielding the most accurate morphology, while LAE-only selections retain bubble-scale topology but with reduced fidelity. Robustness tests show that the method is stable to variations in ionization conditions between training and test data, and to realistic redshift uncertainties. Our results suggest that galaxy-based tomography can potentially deliver reliable reionization maps across realistic survey redshift windows.

astro-ph.CO↗
arXiv2026

Weakly Supervised Tabla Stroke Transcription via TI-SDRM: A Rhythm-Aware Lattice Rescoring Framework

Tabla Stroke Transcription (TST) is central to the analysis of rhythmic structure in Hindustani classical music, yet remains challenging due to complex rhythmic organization and the scarcity of strongly annotated data. Existing approaches largely rely on fully supervised learning with onset-level annotations, which are costly and impractical at scale. This work addresses TST in a weakly supervised setting, using only symbolic stroke sequences without temporal alignment. We propose a framework that combines a CTC-based acoustic model with sequence-level rhythmic rescoring. The acoustic model produces a decoding lattice, which is refined using a \textbf{$T\bar{a}la$}-Independent Static--Dynamic Rhythmic Model (TI-SDRM) that integrates long-term rhythmic structure with short-term adaptive dynamics through an adaptive interpolation mechanism. We curate a new real-world tabla solo dataset and a complementary synthetic dataset, establishing the first benchmark for weakly supervised TST in Hindustani classical music. Experiments demonstrate consistent and substantial reductions in stroke error rate over acoustic-only decoding, confirming the importance of explicit rhythmic structure for accurate transcription.

eess.AS↗
arXiv2026

Learning from Limited Labels: Transductive Graph Label Propagation for Indian Music Analysis

Supervised machine learning frameworks rely on extensive labeled datasets for robust performance on real-world tasks. However, there is a lack of large annotated datasets in audio and music domains, as annotating such recordings is resource-intensive, laborious, and often require expert domain knowledge. In this work, we explore the use of label propagation (LP), a graph-based semi-supervised learning technique, for automatically labeling the unlabeled set in an unsupervised manner. By constructing a similarity graph over audio embeddings, we propagate limited label information from a small annotated subset to a larger unlabeled corpus in a transductive, semi-supervised setting. We apply this method to two tasks in Indian Art Music (IAM): Raga identification and Instrument classification. For both these tasks, we integrate multiple public datasets along with additional recordings we acquire from Prasar Bharati Archives to perform LP. Our experiments demonstrate that LP significantly reduces labeling overhead and produces higher-quality annotations compared to conventional baseline methods, including those based on pretrained inductive models. These results highlight the potential of graph-based semi-supervised learning to democratize data annotation and accelerate progress in music information retrieval.

eess.AS↗
arXiv2025

BEST-STD2.0: Balanced and Efficient Speech Tokenizer for Spoken Term Detection

Fast and accurate spoken content retrieval is vital for applications such as voice search. Query-by-Example Spoken Term Detection (STD) involves retrieving matching segments from an audio database given a spoken query. Token-based STD systems, which use discrete speech representations, enable efficient search but struggle with robustness to noise and reverberation, and with inefficient token utilization. We address these challenges by proposing a noise and reverberation-augmented training strategy to improve tokenizer robustness. In addition, we introduce optimal transport-based regularization to ensure balanced token usage and enhance token efficiency. To further speed up retrieval, we adopt a TF-IDF-based search mechanism. Empirical evaluations demonstrate that the proposed method outperforms STD baselines across various distortion levels while maintaining high search efficiency.

eess.AS↗
arXiv2025

Continual Learning for Singing Voice Separation with Human in the Loop Adaptation

Deep learning-based works for singing voice separation have performed exceptionally well in the recent past. However, most of these works do not focus on allowing users to interact with the model to improve performance. This can be crucial when deploying the model in real-world scenarios where music tracks can vary from the original training data in both genre and instruments. In this paper, we present a deep learning-based interactive continual learning framework for singing voice separation that allows users to fine-tune the vocal separation model to conform it to new target songs. We use a U-Net-based base model architecture that produces a mask for separating vocals from the spectrogram, followed by a human-in-the-loop task where the user provides feedback by marking a few false positives, i.e., regions in the extracted vocals that should have been silence. We propose two continual learning algorithms. Experiments substantiate the improvement in singing voice separation performance by the proposed algorithms over the base model in intra-dataset and inter-dataset settings.

cs.SD↗
arXiv2025

AudioNet: Supervised Deep Hashing for Retrieval of Similar Audio Events

This work presents a supervised deep hashing method for retrieving similar audio events. The proposed method, named AudioNet, is a deep-learning-based system for efficient hashing and retrieval of similar audio events using an audio example as a query. AudioNet achieves high retrieval performance on multiple standard datasets by generating binary hash codes for similar audio events, setting new benchmarks in the field, and highlighting its efficacy and effectiveness compare to other hashing methods. Through comprehensive experiments on standard datasets, our research represents a pioneering effort in evaluating the retrieval performance of similar audio events. A novel loss function is proposed which incorporates weighted contrastive and weighted pairwise loss along with hashcode balancing to improve the efficiency of audio event retrieval. The method adopts discrete gradient propagation, which allows gradients to be propagated through discrete variables during backpropagation. This enables the network to optimize the discrete hash codes using standard gradient-based optimization algorithms, which are typically used for continuous variables. The proposed method showcases promising retrieval performance, as evidenced by the experimental results, even when dealing with imbalanced datasets. The systematic analysis conducted in this study further supports the significant benefits of the proposed method in retrieval performance across multiple datasets. The findings presented in this work establish a baseline for future studies on the efficient retrieval of similar audio events using deep audio embeddings.

eess.AS↗
arXiv2025

SCORENF: Score-based Normalizing Flows for Sampling Unnormalized distributions

Unnormalized probability distributions are central to modeling complex physical systems across various scientific domains. Traditional sampling methods, such as Markov Chain Monte Carlo (MCMC), often suffer from slow convergence, critical slowing down, poor mode mixing, and high autocorrelation. In contrast, likelihood-based and adversarial machine learning models, though effective, are heavily data-driven, requiring large datasets and often encountering mode covering and mode collapse. In this work, we propose ScoreNF, a score-based learning framework built on the Normalizing Flow (NF) architecture, integrated with an Independent Metropolis-Hastings (IMH) module, enabling efficient and unbiased sampling from unnormalized target distributions. We show that ScoreNF maintains high performance even with small training ensembles, thereby reducing reliance on computationally expensive MCMC-generated training data. We also present a method for assessing mode-covering and mode-collapse behaviours. We validate our method on synthetic 2D distributions (MOG-4 and MOG-8) and the high-dimensional $\phi^4$ lattice field theory distribution, demonstrating its effectiveness for sampling tasks.

cs.LG↗
arXiv2025

Improving Active Learning for Melody Estimation by Disentangling Uncertainties

Estimating the fundamental frequency, or melody, is a core task in Music Information Retrieval (MIR). Various studies have explored signal processing, machine learning, and deep-learning-based approaches, with a very recent focus on utilizing uncertainty in active learning settings for melody estimation. However, these approaches do not investigate the relative effectiveness of different uncertainties. In this work, we follow a framework that disentangles aleatoric and epistemic uncertainties to guide active learning for melody estimation. Trained on a source dataset, our model adapts to new domains using only a small number of labeled samples. Experimental results demonstrate that epistemic uncertainty is more reliable for domain adaptation with reduced labeling effort as compared to aleatoric uncertainty.

eess.AS↗
arXiv2025

CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents

Text-guided sound separation enables flexible audio editing, assistive listening, and open-domain source extraction, but systems such as AudioSep remain too expensive for low-latency edge or codec-mediated deployment. Existing neural audio codec separators are efficient, yet largely restricted to fixed stems or closed taxonomies. We introduce CodecSep, a prompt-driven universal sound separation framework that extracts sources directly in neural audio codec latent space. CodecSep combines a frozen DAC backbone with a lightweight FiLM-conditioned Transformer masker driven by CLAP text embeddings, enabling open-vocabulary separation while preserving codec-native efficiency. Across dnr-v2 and five open-domain benchmarks, CodecSep consistently improves over AudioSep in SI-SDR, remains competitive in ViSQOL, and achieves clear gains in human MOS-LQS. Controlled analyses show that fine-grained prompts outperform coarse labels, and that explicit latent masking is substantially more effective than decoder-style latent generation in codec space. Qualitative diagnostics show that neural audio codec latents retain source-dependent structure, which CodecSep exploits mainly through channel-wise source-conditioned modulation. CodecSep also provides a practical code-stream deployment path. When audio is transmitted as neural audio codec codes, CodecSep maps codes to embeddings, separates directly in codec space, and outputs waveforms or re-quantized codes, avoiding the decode-separate-re-encode loop. In this regime, CodecSep requires only 1.35 GMACs end-to-end: about 54 times less compute than AudioSep in the same pipeline and 25 times lower separator-only compute, with much lower latency and memory. More broadly, CodecSep offers a blueprint for codec-native downstream audio processing.

cs.SD↗