Zobrazeno 1 - 10
of 10
pro vyhledávání: '"singh, Abhayjeet"'
In this paper, we present a 170.83 hour Indian English spontaneous speech dataset. Lack of Indian English speech data is one of the major hindrances in developing robust speech systems which are adapted to the Indian speech style. Moreover this scarc
Externí odkaz:
http://arxiv.org/abs/2312.00698
Autor:
Bandekar, Jesuraj, Udupa, Sathvik, Singh, Abhayjeet, Jayakumar, Anjali, G, Deekshitha, Badiger, Sandhya, Kumar, Saurabh, VH, Pooja, Ghosh, Prasanta Kumar
With the advent of high-quality speech synthesis, there is a lot of interest in controlling various prosodic attributes of speech. Speaking rate is an essential attribute towards modelling the expressivity of speech. In this work, we propose a novel
Externí odkaz:
http://arxiv.org/abs/2310.08846
Autor:
Singh, Abhayjeet, Mehta, Arjun Singh, S, Ashish Khuraishi K, G, Deekshitha, Date, Gauri, Nanavati, Jai, Bandekar, Jesuraja, Basumatary, Karnalius, P, Karthika, Badiger, Sandhya, Udupa, Sathvik, Kumar, Saurabh, Savitha, Ghosh, Prasanta Kumar, V, Prashanthi, Pai, Priyanka, Nanavati, Raoul, Saxena, Rohan, Mora, Sai Praneeth Reddy, Raghavan, Srinivasa
Automatic speech recognition (ASR) performance has improved drastically in recent years, mainly enabled by self-supervised learning (SSL) based acoustic models such as wav2vec2 and large-scale multi-lingual training like Whisper. A huge challenge sti
Externí odkaz:
http://arxiv.org/abs/2307.07948
Autor:
Singh, Abhayjeet, MV, Achuth Rao, Vaideeswaran, Rakesh, Yarra, Chiranjeevi, Ghosh, Prasanta Kumar
In this study, listeners of varied Indian nativities are asked to listen and recognize TIMIT utterances spoken by American speakers. We have three kinds of responses from each listener while they recognize an utterance: 1. Sentence difficulty ratings
Externí odkaz:
http://arxiv.org/abs/2112.04151
We estimate articulatory movements in speech production from different modalities - acoustics and phonemes. Acoustic-to articulatory inversion (AAI) is a sequence-to-sequence task. On the other hand, phoneme to articulatory (PTA) motion estimation fa
Externí odkaz:
http://arxiv.org/abs/2104.05017
While speaking at different rates, articulators (like tongue, lips) tend to move differently and the enunciations are also of different durations. In the past, affine transformation and DNN have been used to transform articulatory movements from neut
Externí odkaz:
http://arxiv.org/abs/2006.03107
Unlike phoneme sequences, movements of speech articulators (lips, tongue, jaw, velum) and the resultant acoustic signal are known to encode not only the linguistic message but also carry para-linguistic information. While several works exist for esti
Externí odkaz:
http://arxiv.org/abs/1910.14375
Autor:
singh, Abhayjeet1 abhayjeets@yahoo.com, Lanke, Rama Brahmam2, Shetty, Rakhith3, Akifuddin, Syed4, Sahu, Manish5, singh, Navneet6, Kaur, Gagandeep6, Goyal, Garish7
Publikováno v:
Journal of Clinical & Diagnostic Research. Oct2015, Vol. 9 Issue 10, p49-52. 4p.
Autor:
SINGH, HARKANWAL PREET, SHETTY, SUJAN, PATIL, PRASHANT, SETHI, NEERJA, SINGH, ABHAYJEET, RAGHUNANDAN, B. N.
Publikováno v:
Journal of Clinical & Diagnostic Research; Aug2014, Vol. 8 Issue 8, p16-18, 3p
Autor:
Alexey Karpov, K. Samudravijaya, K. T. Deepak, Rajesh M. Hegde, Shyam S. Agrawal, S. R. Mahadeva Prasanna
The two-volume proceedings set LNAI 14338 and 14339 constitutes the refereed proceedings of the 25th International Conference on Speech and Computer, SPECOM 2023, held in Dharwad, India, during November 29–December 2, 2023.The 94 papers included i