mlsanityData to 14 Oct 2026

Unified Modeling of Multi-Domain Multi-Device ASR Systems

arXiv 2205.06655 ↗First posted 13 May 2022cs.CL cs.SD eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Modern Automatic Speech Recognition (ASR) systems often use a portfolio of domain-specific models in order to get high accuracy for distinct user utterance types across different devices. In this paper, we propose an innovative approach that integrates the different per-domain per-device models into a unified model, using a combination of domain embedding, domain experts, mixture of experts and adversarial training. We run careful ablation studies to show the benefit of each of these innovations in contributing to the accuracy of the overall unified model. Experiments show that our proposed unified modeling approach actually outperforms the carefully tuned per-domain models, giving relative gains of up to 10% over a baseline model with negligible increase in the number of parameters.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 16 of its 22 references that are in the map. First posted on arXiv 13 May 2022.

Builds on

16 of 22 references.

References · 16

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  5. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  6. 2021Scaling Vision with Sparse Mixture of Expertscited by 747
  7. 2021DEMix Layers: Disentangling Domains for Modular Language Modelingcited by 132
  8. 2020Contextual RNN-T For Open Domain ASRcited by 85
  9. 2020Attention based on-device streaming speech recognition with large speech corpuscited by 18
  10. 2020REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabelingcited by 18
  11. 2018Building a Unified Code-Switching ASR System for South African Languagescited by 12
  12. 2019Semi-supervised acoustic model training for five-lingual code-switched ASRcited by 9
4 more
  1. 2021Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-Endcited by 8
  2. 2019AD3: Attentive Deep Document Datercited by 6
  3. 2021Improving RNN-T ASR Performance with Date-Time and Location Awarenesscited by 2
  4. 2021A Mixture of Expert Based Deep Neural Network for Improved ASRcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognitioncited by 1
  2. 2024Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognitioncited by 1
  3. 2024An Efficient Self-Learning Framework For Interactive Spoken Dialog Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
  2. 2023Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models
  3. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
  4. 2023TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
  5. 2024Progressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training
  6. 2023Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation
  7. 2025Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models
  8. 2026Entropy-Aware Domain-Routed Mixture-of-Experts Speech-LLM Framework: A Case Study of Multi-Domain Child-Adult ASR