Related papers: Romanized to Native Malayalam Script Transliterati…

Current end-to-end approaches to Spoken Language Translation (SLT) rely on limited training resources, especially for multilingual settings. On the other hand, Multilingual Neural Machine Translation (MultiNMT) approaches rely on…

The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters…

The field of neural machine translation (NMT) has changed with the advent of large language models (LLMs). Much of the recent emphasis in natural language processing (NLP) has been on modeling machine translation and many other problems…

Speech brain--computer interfaces require decoders that translate intracortical activity into linguistic output while remaining robust to limited data and day-to-day variability. While prior high-performing systems have largely relied on…

Transformer-based pre-trained language models have dominated the field of Natural Language Processing (NLP) for quite some time now. However, the Nepali language, spoken by approximately 32 million people worldwide, remains significantly…

Mapping speech tokens to the same feature space as text tokens has become the paradigm for the integration of speech modality into decoder-only large language models (LLMs). An alternative approach is to use an encoder-decoder architecture…

Recognition of handwritten Roman characters and numerals has been extensively studied in the last few decades and its accuracy reached to a satisfactory state. But the same cannot be said while talking about the Devanagari script which is…

While neural, encoder-decoder models have had significant empirical success in text generation, there remain several unaddressed problems with this style of generation. Encoder-decoder models are largely (a) uninterpretable, and (b)…

An end-to-end (E2E) ASR model implicitly learns a prior Internal Language Model (ILM) from the training transcripts. To fuse an external LM using Bayes posterior theory, the log likelihood produced by the ILM has to be accurately estimated…

This paper reports about our work in the ICON 2013 NLP TOOLS CONTEST on Named Entity Recognition. We submitted runs for Bengali, English, Hindi, Marathi, Punjabi, Tamil and Telugu. A statistical HMM (Hidden Markov Models) based model has…

The recent surge of complex attention-based deep learning architectures has led to extraordinary results in various downstream NLP tasks in the English language. However, such research for resource-constrained and morphologically rich…

With the rapid development of Large Language Models (LLMs), a large number of benchmarks have been proposed. However, most benchmarks lack unified evaluation standard and require the manual implementation of custom scripts, making results…

While Large Language Models (LLMs) have significantly advanced Text-to-SQL performance, existing benchmarks predominantly focus on Western contexts and simplified schemas, leaving a gap in real-world, non-Western applications. We present…

We train a bilingual Arabic-Hebrew language model using a transliterated version of Arabic texts in Hebrew, to ensure both languages are represented in the same script. Given the morphological, structural similarities, and the extensive…

Text generation with Large Language Models (LLMs) is known to be memory bound due to the combination of their auto-regressive nature, huge parameter counts, and limited memory bandwidths, often resulting in low token rates. Speculative…

The success in designing Code-Switching (CS) ASR often depends on the availability of the transcribed CS resources. Such dependency harms the development of ASR in low-resourced languages such as Bengali and Hindi. In this paper, we exploit…

This paper describes the systems developed by SPRING Lab, Indian Institute of Technology Madras, for the ASRU MADASR 2.0 challenge. The systems developed focuses on adapting ASR systems to improve in predicting the language and dialect of…

Transliteration has emerged as a promising means to bridge the gap between various languages in multilingual NLP, showing promising results especially for languages using non-Latin scripts. We investigate the degree to which shared script,…

The multi-decoder (MD) end-to-end speech translation model has demonstrated high translation quality by searching for better intermediate automatic speech recognition (ASR) decoder states as hidden intermediates (HI). It is a two-pass…

This paper presents a novel hybrid tokenization strategy that enhances the performance of DNA Language Models (DLMs) by combining 6-mer tokenization with Byte Pair Encoding (BPE-600). Traditional k-mer tokenization is effective at capturing…