Responsible ASR: Overcoming Challenges of Foundational Models in Narrow-Band and Low-Resource Settings
It highlights persistent challenges for ASR in telephony and low-resource settings, but the findings are incremental and confirm known limitations.
This paper evaluates foundational ASR models on narrow-band, low-resource Hindi and Indian-accented English, finding suboptimal zero-shot performance and limited improvement from fine-tuning with small datasets.
Telephony conversations worldwide are conducted over narrow-band channels and are often spontaneous and colloquial in nature. This paper evaluates the performance of widely used foundational automatic speech recognition (ASR) models -- both open-source and commercial -- on narrow-band conversations in Hindi, a low-resource language, and Indian-accented English, a low-resource accent. We first assess these models in a zero-shot setting and find that their performance remains suboptimal across the board. Highlighting the challenges faced by ASR models in narrow-band and low-resource language scenarios, we further investigate the impact of fine-tuning open-source models using a limited set of real-life annotated recordings. Our findings indicate that while fine-tuning provides some improvements, its effectiveness varies across languages and accents, largely influenced by the amount of data encountered during pretraining