mlsanityData to 7 Oct 2026

Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking

arXiv 2409.18428 ↗First posted 27 Sep 2024cs.CL cs.SD eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

Multilingual Automatic Speech Recognition (ASR) models are typically evaluated in a setting where the ground-truth language of the speech utterance is known, however, this is often not the case for most practical settings. Automatic Spoken Language Identification (SLID) models are not perfect and misclassifications have a substantial impact on the final ASR accuracy. In this paper, we present a simple and effective N-best re-ranking approach to improve multilingual ASR accuracy for several prominent acoustic models by employing external features such as language models and text-based language identification models. Our results on FLEURS using the MMS and Whisper models show spoken language identification accuracy improvements of 8.7% and 6.1%, respectively and word error rates which are 3.3% and 2.0% lower on these benchmarks.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 27 Sep 2024.

Builds on

21 of 29 references.

References · 21

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  2. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  3. 2015Listen, Attend and Spellcited by 542
  4. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 458
  5. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  6. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  7. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languagescited by 228
  8. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  9. 2023End-to-End Speech Recognition: A Surveycited by 127
  10. 2023SeamlessM4T: Massively Multilingual & Multimodal Machine Translationcited by 124
  11. 2017Multilingual Speech Recognition With A Single End-To-End Modelcited by 87
  12. 2023ML-SUPERB: Multilingual Speech Universal PERformance Benchmarkcited by 70
9 more
  1. 2017Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Modelcited by 37
  2. 2023Improving Massively Multilingual ASR With Auxiliary CTC Objectivescited by 31
  3. 2024MaLA-500: Massive Language Adaptation of Large Language Modelscited by 28
  4. 2022ASR2K: Speech Recognition for Around 2000 Languages without Audiocited by 26
  5. 2021Joint Modeling of Code-Switched and Monolingual ASR via Conditional Factorizationcited by 17
  6. 2022Towards Zero-Shot Code-Switched Speech Recognitioncited by 15
  7. 2024Scaling A Simple Approach to Zero-Shot Speech Recognitioncited by 8
  8. 2019Signal Combination for Language Identificationcited by 4
  9. 2020Streaming Language Identification using Combination of Acoustic Representations and ASR Hypothesescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Efficient Multilingual ASR Finetuning via LoRA Language Expertscited by 5
  2. 2026Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulationcited by 3