Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Tulsiani, Hitesh"'
Autor:
Tulsiani, Hitesh, Chan, David M., Ghosh, Shalini, Lalwani, Garima, Pandey, Prabhat, Bansal, Ankish, Garimella, Sri, Rastrow, Ariya, Hoffmeister, Björn
Dialog systems, such as voice assistants, are expected to engage with users in complex, evolving conversations. Unfortunately, traditional automatic speech recognition (ASR) systems deployed in such applications are usually trained to recognize each
Externí odkaz:
http://arxiv.org/abs/2409.10515
While word error rates of automatic speech recognition (ASR) systems have consistently fallen, natural language understanding (NLU) applications built on top of ASR systems still attribute significant numbers of failures to low-quality speech recogni
Externí odkaz:
http://arxiv.org/abs/2401.02417
Autor:
Swarup, Prakhar, Chakrabarty, Debmalya, Sapru, Ashtosh, Tulsiani, Hitesh, Arsikere, Harish, Garimella, Sri
Semi-supervised learning (SSL) is an active area of research which aims to utilize unlabelled data in order to improve the accuracy of speech recognition systems. The current study proposes a methodology for integration of two key ideas: 1) SSL using
Externí odkaz:
http://arxiv.org/abs/2008.03923
Publikováno v:
2014 Twentieth National Conference on Communications (NCC); 2014, p1-6, 6p