Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Kulshreshtha, Devang"'
Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining models on both existing and new domains. Fine-tuning solely on new domai
Externí odkaz:
http://arxiv.org/abs/2406.17935
Autor:
Jayanthi, Sai Muralidhar, Kulshreshtha, Devang, Dingliwal, Saket, Ronanki, Srikanth, Bodapati, Sravan
Personalization of automatic speech recognition (ASR) models is a widely studied topic because of its many practical applications. Most recently, attention-based contextual biasing techniques are used to improve the recognition of rare words and doma
Externí odkaz:
http://arxiv.org/abs/2311.08402
Autor:
Elluru, Veera Raghavendra, Kulshreshtha, Devang, Paturi, Rohit, Bodapati, Sravan, Ronanki, Srikanth
Spoken language understanding systems using audio-only data are gaining popularity, yet their ability to handle unseen intents remains limited. In this study, we propose a generalized zero-shot audio-to-intent classification framework with only a few
Externí odkaz:
http://arxiv.org/abs/2311.02482
Connectionist Temporal Classification (CTC) models are popular for their balance between speed and performance for Automatic Speech Recognition (ASR). However, these CTC models still struggle in other areas, such as personalization towards custom wor
Externí odkaz:
http://arxiv.org/abs/2307.00759
Autor:
Das, Nilaksh, Sunkara, Monica, Bodapati, Sravan, Cai, Jinglun, Kulshreshtha, Devang, Farris, Jeff, Kirchhoff, Katrin
End-to-end ASR models trained on large amount of data tend to be implicitly biased towards language semantics of the training data. Internal language model estimation (ILME) has been proposed to mitigate this bias for autoregressive models such as at
Externí odkaz:
http://arxiv.org/abs/2305.03837
Autor:
Kulshreshtha, Devang, Shayan, Muhammad, Belfer, Robert, Reddy, Siva, Serban, Iulian Vlad, Kochmar, Ekaterina
Existing work on generating hints in Intelligent Tutoring Systems (ITS) focuses mostly on manual and non-personalized feedback. In this work, we explore automatically generated questions as personalized feedback in an ITS. Our personalized feedback c
Externí odkaz:
http://arxiv.org/abs/2206.04187
In this work, we introduce back-training, an alternative to self-training for unsupervised domain adaptation (UDA) from source to target domain. While self-training generates synthetic training data where natural inputs are aligned with noisy outputs
Externí odkaz:
http://arxiv.org/abs/2104.08801