Vedavani: A Benchmark Corpus for ASR on Vedic Sanskrit Poetry

TL;DR

Vedavani introduces a pioneering ASR dataset and benchmark for Vedic Sanskrit poetry, addressing unique phonetic challenges and enabling future research in this ancient language's speech recognition.

Contribution

The paper presents the first comprehensive Sanskrit Vedic poetry ASR dataset and benchmarks multiple models, highlighting IndicWhisper's superior performance.

Findings

IndicWhisper achieved the best results among tested models.

The dataset captures prosodic and rhythmic features of Vedic Sanskrit.

This work advances ASR research for ancient and poetic languages.

Abstract

Sanskrit, an ancient language with a rich linguistic heritage, presents unique challenges for automatic speech recognition (ASR) due to its phonemic complexity and the phonetic transformations that occur at word junctures, similar to the connected speech found in natural conversations. Due to these complexities, there has been limited exploration of ASR in Sanskrit, particularly in the context of its poetic verses, which are characterized by intricate prosodic and rhythmic patterns. This gap in research raises the question: How can we develop an effective ASR system for Sanskrit, particularly one that captures the nuanced features of its poetic form? In this study, we introduce Vedavani, the first comprehensive ASR study focused on Sanskrit Vedic poetry. We present a 54-hour Sanskrit ASR dataset, consisting of 30,779 labelled audio samples from the Rig Veda and Atharva Veda. This dataset captures the precise prosodic and rhythmic features that define the language. We also benchmark the dataset on various state-of-the-art multilingual speech models.$^{1}$ Experimentation revealed that IndicWhisper performed the best among the SOTA models.