-
Dec 24, 2024 | 
amazon.science | Karel Mundnich |Xing Niu |Prashant Mathur |Srikanth Ronanki
Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose to leverage a multilingual Large Language Model (LLM) to perform ST and ASR in languages for which the model has never seen paired audio-text data.
-
Jul 31, 2024 | 
amazon.science | Lucas Brandão Gonçalves |Prashant Mathur |Chandrashekhar Lavania |Metehan Cekic
Recent advancements in audio-visual generative modeling have been propelled by progress in deep learning and the availability of data-rich benchmarks. However, the growth is not attributed solely to models and benchmarks. Universally accepted evaluation metrics also play an important role in advancing the field.
-
Jul 29, 2024 | 
amazon.science | Lucas Brandão Gonçalves |Prashant Mathur |Chandrashekhar Lavania |Metehan Cekic
Recent advancements in audio-visual generative modeling have been propelled by progress in deep learning and the availability of data-rich benchmarks. However, the growth is not attributed solely to models and benchmarks. Universally accepted evaluation metrics also play an important role in advancing the field.
-
Jul 19, 2024 | 
amazon.science | Chandrashekhar Lavania |Prashant Mathur |Kyu S. Han |Georgios Chochlakis
Audio-visual representations leverage information from both modalities to produce joint representations. Such representations have demonstrated their usefulness in a variety of tasks. However, both modalities incorporated in the learned model might not necessarily be present all the time during inference. In this work, we study whether and how we can make exist- ing models, trained under pristine conditions, robust to partial modality loss without retraining them.
-
Jul 3, 2024 | 01345-x/fulltext?dgcid=twitter_organic_comment24_lancet&sz=64)
thelancet.com | Claudia Allemani |Prashant Mathur |Michel P Coleman
The global burden of cancer is immense, it is increasing, and it afflicts low-income and middle-income countries more severely than high-income countries. In some countries, total national expenditure on health has fallen in real terms, reducing the capacity to manage the backlogs in patient care that arose during the COVID-19 pandemic.
-
Jun 25, 2024 | 
amazon.science | Yogesh Virkar |Prashant Mathur |Proyag Pal |Brian Thompson
To translate speech for automatic dubbing, machine translation needs to be isochronous, i.e. translated speech needs to be aligned with the source in terms of speech durations. We introduce target factors in a transformer model to predict durations jointly with target language phoneme sequences. We also introduce auxiliary counters to help the decoder to keep track of the timing information while generating target phonemes.
-
Apr 26, 2024 | 
onlinelibrary.wiley.com | Prashant Mathur |Research Bengaluru India |Thilagavathi Ramamoorthy |Sudarshan Kondalli Lakshminarayana
Aim The coronavirus disease 2019 (COVID-19) pandemic affected cancer service delivery and the feasibility of following the standard treatment guidelines. The present paper describes the use of clinical care guidelines for cancer management in routine practice and the approach adopted towards cancer care during the COVID-19 pandemic in India.
-
Apr 10, 2024 | 
arxiv.org | Prashant Mathur |Chandrashekhar Lavania |Marcello Federico |Metehan Cekic
-
Nov 22, 2023 | 
amazon.science | Surafel Melaku Lakew |Yogesh Virkar |Prashant Mathur |Marcello Federico
Automatic dubbing (AD) is among the machine translation (MT) use cases where translations should match a given length to allow for synchronicity between source and target speech. For neural MT, generating translations of length close to the source length (e.g. within ±10% in character count), while preserving quality is a challenging task.
-
Jun 19, 2023 | 00095-1/abstract&sz=64)
thelancet.com | Anita Nath |Prashant Mathur |K.L. Sudarshan |Gurpreet Kaur Rajput
SummaryChildhood cancers are emerging as an essential concern in India where there is lack of a specific programme component or policy to address childhood cancer control. There is limited information on the status and quality of childhood cancer care services in India. This paper describes the childhood cancer care services available at secondary and tertiary-level hospitals in India through a cross sectional study design.
