Author name cluster

Saurabh Kumar

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

NeurIPS Conference 2025 Conference Paper

RESPIN-S1.0: A read speech corpus of 10000+ hours in dialects of nine Indian Languages

Saurabh Kumar
Abhayjeet Singh
DEEKSHITHA G
Amartya veer
Jesuraj Bandekar
Savitha Murthy
Sumit Sharma
Sandhya Badiger

We introduce RESPIN-S1. 0, the largest publicly available dialect-rich read-speech corpus for Indian languages, comprising more than 10, 000 hours of validated audio across nine major languages: Bengali, Bhojpuri, Chhattisgarhi, Hindi, Kannada, Magahi, Maithili, Marathi, and Telugu. Indian languages exhibit high dialectal variation and are spoken by populations that remain digitally underserved. Existing speech corpora typically represent only standard dialects and lack domain and linguistic diversity. RESPIN-S1. 0 addresses this limitation by collecting speech across more than 38 dialects and two high-impact domains: agriculture and finance. Text data were composed by native dialect speakers and validated through a pipeline combining automated and manual checks. Over 200, 000 unique sentences were recorded through a crowdsourced mobile platform and categorised into clean, semi-noisy, and noisy subsets based on transcription quality, with the clean portion alone exceeding 10, 000 hours. Along with audio and transcriptions, RESPIN provides dialect-aware phonetic lexicons, speaker metadata, and reproducible train, development, and test splits. To benchmark performance, we evaluate multiple ASR models, including TDNN-HMM, E-Branchformer, Whisper, and wav2vec2-based self-supervised models, and find that fine-tuning on RESPIN significantly improves recognition accuracy over pretrained baselines. A subset of RESPIN-S1. 0 has already supported community challenges such as the SLT Code Hackathon 2022 and MADASR@ASRU 2023 and 2025, releasing more than 1, 200 hours publicly. This resource supports research in dialectal ASR, language identification, and related speech technologies, establishing a comprehensive benchmark for inclusive, dialect-rich ASR in multilingual low-resource settings. Dataset: https: //spiredatasets. ee. iisc. ac. in/respincorpus Code: https: //github. com/labspire/respin_baselines. git

PDF Details

NeurIPS Conference 2020 Conference Paper

Gradient Surgery for Multi-Task Learning

Tianhe Yu
Saurabh Kumar
Abhishek Gupta
Sergey Levine
Karol Hausman
Chelsea Finn

While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, data efficiency remains a major challenge. Multi-task learning has emerged as a promising approach for sharing structure across multiple tasks to enable more efficient learning. However, the multi-task setting presents a number of optimization challenges, making it difficult to realize large efficiency gains compared to learning tasks independently. The reasons why multi-task learning is so challenging compared to single-task learning are not fully understood. In this work, we identify a set of three conditions of the multi-task optimization landscape that cause detrimental gradient interference, and develop a simple yet general approach for avoiding such interference between task gradients. We propose a form of gradient surgery that projects a task's gradient onto the normal plane of the gradient of any other task that has a gradient. On a series of challenging multi-task supervised and multi-task RL problems, this approach leads to substantial gains in efficiency and performance. Further, it is model-agnostic and can be combined with previously-proposed multi-task architectures for enhanced performance.

PDF Details

NeurIPS Conference 2020 Conference Paper

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL

Saurabh Kumar
Aviral Kumar
Sergey Levine
Chelsea Finn

While reinforcement learning algorithms can learn effective policies for complex tasks, these policies are often brittle to even minor task variations, especially when variations are not explicitly provided during training. One natural approach to this problem is to train agents with manually specified variation in the training task or environment. However, this may be infeasible in practical situations, either because making perturbations is not possible, or because it is unclear how to choose suitable perturbation strategies without sacrificing performance. The key insight of this work is that learning diverse behaviors for accomplishing a task can directly lead to behavior that generalizes to varying environments, without needing to perform explicit perturbations during training. By identifying multiple solutions for the task in a single environment during training, our approach can generalize to new situations by abandoning solutions that are no longer effective and adopting those that are. We theoretically characterize a robustness set of environments that arises from our algorithm and empirically find that our diversity-driven approach can extrapolate to various changes in the environment and task.

PDF Details

RLDM Conference 2017 Conference Abstract

State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learn- ing

Saurabh Kumar
Himanshu Sahni
Farhan Tejani
Yannick Schroecker
Charles Isbell

Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, simpler domains to more complex ones using a recurrent attention mechanism. The task is presented to the agent as an image and an instruction specifying the goal. This meta-controller guides the agent towards its goal by designing a sequence of smaller sub-tasks on the part of the state space within the attention, effectively decomposing it. As a baseline, we consider a setup without attention as well. Our experiments show that the meta-controller learns to create subgoals within the attention.

PDF Details