4 citations · 14 across the 18 of their papers we have counts for
13 papers · 1 filter
Vimarsha: Faithful ASR Evaluation for Indian Languages with Demographic Diversity, In-the-Wild Audio and Spelling Variations
Kaushal Santosh Bhogale, Srija Anand, Sadakopa Ramakrishnan Thothathiri +3
Evaluation benchmarks for Indian language automatic speech recognition (ASR) suffer from two systematic biases: optimistic scores from clean, controlled audio conditions, and pessi…
Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages
Deovrat Mehendale, Aditya Mehndiratta, Dhruv Rathi +2
In this work, we introduce Indic DiarBench, a speaker diarization and ASR benchmark dataset spanning all 22 scheduled languages of India. This corpus comprises approximately 108 ho…
Voice of India: A Large-Scale Benchmark for Real-World Speech Recognition in India
Kaushal Bhogale, Manas Dhir, Amritansh Walecha +11
Existing Indic ASR benchmarks often use scripted, clean speech and leaderboard driven evaluation that encourages dataset specific overfitting. In addition, strict single reference…
Towards Orthographically-Informed Evaluation of Speech Recognition Systems for Indian Languages
Kaushal Santosh Bhogale, Tahir Javed, Greeshma Susan John +4
Evaluating ASR systems for Indian languages is challenging due to spelling variations, suffix splitting flexibility, and non-standard spellings in code-mixed words. Traditional Wor…
NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data
Tahir Javed, Kaushal Bhogale, Mitesh M. Khapra
We introduce Nirantar, a comprehensive framework for evaluating continual learning (CL) in multilingual and multi-domain ASR. Designed to reflect real-world CL challenges, Nirantar…
Empowering Low-Resource Language ASR via Large-Scale Pseudo Labeling
Kaushal Santosh Bhogale, Deovrat Mehendale, Niharika Parasa +4
In this study, we tackle the challenge of limited labeled data for low-resource languages in ASR, focusing on Hindi. Specifically, we explore pseudo-labeling, by proposing a generi…
LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR Systems
Tahir Javed, Janki Nawale, Sakshi Joshi +4
Hindi, one of the most spoken language of India, exhibits a diverse array of accents due to its usage among individuals from diverse linguistic origins. To enable a robust evaluati…
IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages
Tahir Javed, Janki Atul Nawale, Eldho Ittan George +18
We present INDICVOICES, a dataset of natural and spontaneous speech containing a total of 7348 hours of read (9%), extempore (74%) and conversational (17%) audio from 16237 speaker…
Svarah: Evaluating English ASR Systems on Indian Accents
Tahir Javed, Sakshi Joshi, Vignesh Nagarajan +6
India is the second largest English-speaking country in the world with a speaker base of roughly 130 million. Thus, it is imperative that automatic speech recognition (ASR) systems…
Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR
Kaushal Santosh Bhogale, Sai Sundaresan, Abhigyan Raman +3
Improving ASR systems is necessary to make new LLM-based use-cases accessible to people across the globe. In this paper, we focus on Indian languages, and make the case that divers…
Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages
Kaushal Santosh Bhogale, Abhigyan Raman, Tahir Javed +4
End-to-end (E2E) models have become the default choice for state-of-the-art speech recognition systems. Such models are trained on large amounts of labelled data, which are often n…
IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages
Tahir Javed, Kaushal Santosh Bhogale, Abhigyan Raman +3
A cornerstone in AI research has been the creation and adoption of standardized training and test datasets to earmark the progress of state-of-the-art models. A particularly succes…
Towards Building ASR Systems for the Next Billion Users
Tahir Javed, Sumanth Doddapaneni, Abhigyan Raman +5
Recent methods in speech and language technology pretrain very LARGE models which are fine-tuned for specific tasks. However, the benefits of such LARGE models are often limited to…