Related papers: Accent Placement Models for Rigvedic Sanskrit Text

This paper explores syllable sequence prediction in Abugida languages using Transformer-based models, focusing on six languages: Bengali, Hindi, Khmer, Lao, Myanmar, and Thai, from the Asian Language Treebank (ALT) dataset. We investigate…

Neural machine translation (NMT) is a recent and effective technique which led to remarkable improvements in comparison of conventional machine translation techniques. Proposed neural machine translation model developed for the Gujarati…

Devan\=agar\=i is the writing system that is adapted by various languages like Sanskrit. International Alphabet of Sanskrit Transliteration (IAST) is a transliteration scheme for romanisation of Sanskrit language. IAST makes use of…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). Accented TTS synthesis is challenging as L2 is different from L1 in both in terms of phonetic rendering and…

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

Automatic Speech Recognition (ASR) is increasingly used to document clinical encounters, yet its reliability in multilingual and demographically diverse Indian healthcare contexts remains largely unknown. In this study, we conduct the first…

Singing Voice Synthesis (SVS) remains constrained in practical deployment due to its strong dependence on accurate phoneme-level alignment and manually annotated melody contours, requirements that are resource-intensive and hinder…

This study demonstrates how hybrid neural-symbolic methods can yield significant new insights into the evolution of a morphologically rich, low-resource language. We challenge the naive assumption that linguistic change is simplification by…

Automatic speech recognition (ASR) is widely used in consumer electronics. ASR greatly improves the utility and accessibility of technology, but usually the output is only word sequences without punctuation. This can result in ambiguity in…

Automatic speech recognition (ASR) systems often encounter difficulties in accurately recognizing rare words, leading to errors that can have a negative impact on downstream tasks such as keyword spotting, intent detection, and text…

Recognition of ancient Tamil characters has always been a challenge for epigraphers. This is primarily because the language has evolved over the several centuries and the character set over this time has both expanded and diversified. This…

Automatic Speech Recognition (ASR) systems generally do not produce punctuated transcripts. To make transcripts more readable and follow the expected input format for downstream language models, it is necessary to add punctuation marks. In…

In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch. We present our findings regarding ResNet-based speaker embedding architectures and show that…

In real-world voice conversion applications, environmental noise in source speech and user demands for expressive output pose critical challenges. Traditional ASR-based methods ensure noise robustness but suppress prosody richness, while…

India is a multilingual multi-script country. In every state of India there are two languages one is state local language and the other is English. For example in Andhra Pradesh, a state in India, the document may contain text words in…

Speech enhancement (SE) is proved effective in reducing noise from noisy speech signals for downstream automatic speech recognition (ASR), where multi-task learning strategy is employed to jointly optimize these two tasks. However, the…

Tokens are the basic units of Large Language Models (LLMs). LLMs rely on tokenizers to segment text into these tokens, and tokenization is the primary determinant of computational and inference cost. Sanskrit, one of the oldest languages,…

Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many AC approaches rely on source-target parallel speech data. We propose a…

Automatic Speech Recognition (ASR) systems are widely used in everyday communication, education, healthcare, and industry, yet their performance remains uneven across speakers, particularly when dialectal variation diverges from the…