mlsanityData to 14 Oct 2026

Building English ASR model with regional language support

arXiv 2503.07522 ↗First posted 10 Mar 2025eess.AS cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a novel approach to developing an English Automatic Speech Recognition (ASR) system that can effectively handle Hindi queries, without compromising its performance on English. We propose a novel acoustic model (AM), referred to as SplitHead with Attention (SHA) model, features shared hidden layers across languages and language-specific projection layers combined via a self-attention mechanism. This mechanism estimates the weight for each language based on input data and weighs the corresponding language-specific projection layers accordingly. Additionally, we propose a language modeling approach that interpolates n-gram models from both English and transliterated Hindi text corpora. Our results demonstrate the effectiveness of our approach, with a 69.3% and 5.7% relative reduction in word error rate on Hindi and English test sets respectively when compared to a monolingual English model.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 29 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

11 of 29 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  3. 2021MuRIL: Multilingual Representations for Indian Languagescited by 179
  4. 2017Transfer Learning for Speech Recognition on a Budgetcited by 25
  5. 2019From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognitioncited by 20
  6. 2020Streaming End-to-End Bilingual ASR Systems with Joint Language Identificationcited by 20
  7. 2018Code-switched Language Models Using Dual RNNs and Same-Source Pretrainingcited by 16
  8. 2018Contextual Language Model Adaptation for Conversational Agentscited by 10
  9. 2020Transfer Learning Approaches for Streaming End-to-End Speech Recognition Systemcited by 10
  10. 2017Dual Language Models for Code Switched Speech Recognitioncited by 5
  11. 2024Streaming Bilingual End-to-End ASR model using Attention over Multiple Softmaxcited by 1

Built on by

Not cited yet.