Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Javed, Tahir"'
Autor:
Javed, Tahir, Nawale, Janki Atul, George, Eldho Ittan, Joshi, Sakshi, Bhogale, Kaushal Santosh, Mehendale, Deovrat, Sethi, Ishvinder Virender, Ananthanarayanan, Aparna, Faquih, Hafsah, Palit, Pratiti, Ravishankar, Sneha, Sukumaran, Saranya, Panchagnula, Tripura, Murali, Sunjay, Gandhi, Kunal Sharad, R, Ambujavalli, M, Manickam K, Vaijayanthi, C Venkata, Karunganni, Krishnan Srinivasa Raghavan, Kumar, Pratyush, Khapra, Mitesh M
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 speakers covering 145 Indian districts and 22 languages. Of these 7348 hours,
Externí odkaz:
http://arxiv.org/abs/2403.01926
Autor:
Javed, Tahir, Joshi, Sakshi, Nagarajan, Vignesh, Sundaresan, Sai, Nawale, Janki, Raman, Abhigyan, Bhogale, Kaushal, Kumar, Pratyush, Khapra, Mitesh M.
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 for English should be evaluated on Indian accents. Unfortunately, Ind
Externí odkaz:
http://arxiv.org/abs/2305.15760
Autor:
Bhogale, Kaushal Santosh, Sundaresan, Sai, Raman, Abhigyan, Javed, Tahir, Khapra, Mitesh M., Kumar, Pratyush
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 diverse benchmarks are required to evaluate and improve ASR systems for Indi
Externí odkaz:
http://arxiv.org/abs/2305.15386
Autor:
Bhogale, Kaushal Santosh, Raman, Abhigyan, Javed, Tahir, Doddapaneni, Sumanth, Kunchukuttan, Anoop, Kumar, Pratyush, Khapra, Mitesh M.
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 not available for low-resource languages. Techniques such as self-super
Externí odkaz:
http://arxiv.org/abs/2208.12666
Autor:
Javed, Tahir, Bhogale, Kaushal Santosh, Raman, Abhigyan, Kunchukuttan, Anoop, Kumar, Pratyush, Khapra, Mitesh M.
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 successful example is the GLUE dataset for training and evaluating Natural L
Externí odkaz:
http://arxiv.org/abs/2208.11761
Autor:
Javed, Tahir, Doddapaneni, Sumanth, Raman, Abhigyan, Bhogale, Kaushal Santosh, Ramesh, Gowtham, Kunchukuttan, Anoop, Kumar, Pratyush, Khapra, Mitesh M.
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 a few resource rich languages of the world. In this work, we make mul
Externí odkaz:
http://arxiv.org/abs/2111.03945
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
In the age of technology, the term IoT (Internet of things) rapidly used in the past few years, forming a smart environment by connecting several objects having communication capabilities over the internet. IoT has large implementations in different
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e15a4954873542078b69e0531164ef9
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.