Zobrazeno 1 - 10
of 144
pro vyhledávání: '"Khapra, Mitesh"'
Autor:
Varadhan, Praveen Srinivasa, Gulati, Amogh, Sankar, Ashwin, Anand, Srija, Gupta, Anirudh, Mukherjee, Anirudh, Marepally, Shiva Kumar, Bhatia, Ankur, Jaju, Saloni, Bhooshan, Suvrat, Khapra, Mitesh M.
Despite rapid advancements in TTS models, a consistent and robust human evaluation framework is still lacking. For example, MOS tests fail to differentiate between similar models, and CMOS's pairwise comparisons are time-intensive. The MUSHRA test is
Externí odkaz:
http://arxiv.org/abs/2411.12719
Autor:
Jain, Sparsh, Sankar, Ashwin, Choudhary, Devilal, Suman, Dhairya, Narasimhan, Nikhil, Khan, Mohammed Safi Ur Rahman, Kunchukuttan, Anoop, Khapra, Mitesh M, Dabre, Raj
Automatic Speech Translation (AST) datasets for Indian languages remain critically scarce, with public resources covering fewer than 10 of the 22 official languages. This scarcity has resulted in AST systems for Indian languages lagging far behind th
Externí odkaz:
http://arxiv.org/abs/2411.04699
Recent advancements in Text-to-Speech (TTS) technology have led to natural-sounding speech for English, primarily due to the availability of large-scale, high-quality web data. However, many other languages lack access to such resources, relying inst
Externí odkaz:
http://arxiv.org/abs/2410.17901
Autor:
Doddapaneni, Sumanth, Khan, Mohammed Safi Ur Rahman, Venkatesh, Dilip, Dabre, Raj, Kunchukuttan, Anoop, Khapra, Mitesh M.
Evaluating machine-generated text remains a significant challenge in NLP, especially for non-English languages. Current methodologies, including automated metrics, human assessments, and LLM-based evaluations, predominantly focus on English, revealin
Externí odkaz:
http://arxiv.org/abs/2410.13394
Autor:
Sankar, Ashwin, Anand, Srija, Varadhan, Praveen Srinivasa, Thomas, Sherry, Singal, Mehak, Kumar, Shridhar, Mehendale, Deovrat, Krishana, Aditi, Raju, Giri, Khapra, Mitesh
Recent advancements in text-to-speech (TTS) synthesis show that large-scale models trained with extensive web data produce highly natural-sounding output. However, such data is scarce for Indian languages due to the lack of high-quality, manually sub
Externí odkaz:
http://arxiv.org/abs/2409.05356
Autor:
Bhogale, Kaushal Santosh, Mehendale, Deovrat, Parasa, Niharika, G, Sathish Kumar Reddy, Javed, Tahir, Kumar, Pratyush, Khapra, Mitesh M.
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 generic framework combining multiple ideas from existing works. Our framewor
Externí odkaz:
http://arxiv.org/abs/2408.14026
Autor:
Javed, Tahir, Nawale, Janki, Joshi, Sakshi, George, Eldho, Bhogale, Kaushal, Mehendale, Deovrat, Khapra, Mitesh M.
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 evaluation of Hindi ASR systems on multiple accents, we create a benchmark, LA
Externí odkaz:
http://arxiv.org/abs/2408.11440
We release Rasa, the first multilingual expressive TTS dataset for any Indian language, which contains 10 hours of neutral speech and 1-3 hours of expressive speech for each of the 6 Ekman emotions covering 3 languages: Assamese, Bengali, & Tamil. Ou
Externí odkaz:
http://arxiv.org/abs/2407.14056
Publicly available TTS datasets for low-resource languages like Hindi and Tamil typically contain 10-20 hours of data, leading to poor vocabulary coverage. This limitation becomes evident in downstream applications where domain-specific vocabulary co
Externí odkaz:
http://arxiv.org/abs/2407.13435
Autor:
Mundra, Nandini, Kishore, Aditya Nanda, Dabre, Raj, Puduppully, Ratish, Kunchukuttan, Anoop, Khapra, Mitesh M.
Language Models (LMs) excel in natural language processing tasks for English but show reduced performance in most other languages. This problem is commonly tackled by continually pre-training and fine-tuning these models for said languages. A signifi
Externí odkaz:
http://arxiv.org/abs/2407.05841