Zobrazeno 1 - 10
of 5 667
pro vyhledávání: '"P Jyothi"'
Spontaneous or conversational multilingual speech presents many challenges for state-of-the-art automatic speech recognition (ASR) systems. In this work, we present a new technique AMPS that augments a multilingual multimodal ASR system with paraphra
Externí odkaz:
http://arxiv.org/abs/2411.18368
Routing and Spectrum Assignment (RSA) represents a significant challenge within Elastic Optical Networks (EONs), particularly in dynamic traffic scenarios where the network undergoes continuous changes. Integrating multiple modulation formats transfo
Externí odkaz:
http://arxiv.org/abs/2411.12442
Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adaptation are two popular methods that have been used to address such low-r
Externí odkaz:
http://arxiv.org/abs/2410.13445
Harnessing pre-trained LLMs to improve ASR systems, particularly for low-resource languages, is now an emerging area of research. Existing methods range from using LLMs for ASR error correction to tightly coupled systems that replace the ASR decoder
Externí odkaz:
http://arxiv.org/abs/2408.16542
Large language models (LLMs) encode vast amounts of world knowledge acquired via training on large web-scale datasets crawled from the internet. However, these datasets typically exhibit a geographical bias towards English-speaking Western countries.
Externí odkaz:
http://arxiv.org/abs/2407.11833
Large language models (LLMs) are very proficient text generators. We leverage this capability of LLMs to generate task-specific data via zero-shot prompting and promote cross-lingual transfer for low-resource target languages. Given task-specific dat
Externí odkaz:
http://arxiv.org/abs/2407.10582
Subword tokens in Indian languages inherently carry meaning, and isolating them can enhance NLP tasks, making sub-word segmentation a crucial process. Segmenting Sanskrit and other Indian languages into subtokens is not straightforward, as it may inc
Externí odkaz:
http://arxiv.org/abs/2407.06331
Speech accents present a serious challenge to the performance of state-of-the-art end-to-end Automatic Speech Recognition (ASR) systems. Even with self-supervised learning and pre-training of ASR models, accent invariance is seldom achieved. In this
Externí odkaz:
http://arxiv.org/abs/2407.03734
Convolutions have become essential in state-of-the-art end-to-end Automatic Speech Recognition~(ASR) systems due to their efficient modelling of local context. Notably, its use in Conformers has led to superior performance compared to vanilla Transfo
Externí odkaz:
http://arxiv.org/abs/2407.03718
Code-switching is a widely prevalent linguistic phenomenon in multilingual societies like India. Building speech-to-text models for code-switched speech is challenging due to limited availability of datasets. In this work, we focus on the problem of
Externí odkaz:
http://arxiv.org/abs/2406.10993