mlsanityData to 14 Oct 2026

Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer

arXiv 2306.08753 ↗First posted 14 Jun 2023eess.AS cs.CL cs.SDcited by 8

Not on the map. Why?

Abstract (arXiv)

Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper proposes (1) a new method for creating code-switching ASR datasets from purely monolingual data sources, and (2) a novel Concatenated Tokenizer that enables ASR models to generate language ID for each emitted text token while reusing existing monolingual tokenizers. The efficacy of these approaches for building CS ASR models is demonstrated for two language pairs, English-Hindi and English-Spanish, where we achieve new state-of-the-art results on the Miami Bangor CS evaluation corpus. In addition to competitive ASR performance, the proposed Concatenated Tokenizer models are highly effective for spoken language identification, achieving 98%+ accuracy on the out-of-distribution FLEURS dataset.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 20 of its 35 references that are in the map. First posted on arXiv 14 Jun 2023.

Builds on

20 of 35 references.

References · 20

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  5. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  6. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 476
  7. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  8. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 463
  9. 2023Scaling Speech Technology to 1,000+ Languagescited by 411
  10. 2020Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameterscited by 110
  11. 2019Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Modelcited by 93
  12. 2019A Survey of Code-switched Speech and Language Processingcited by 75
8 more
  1. 2021Scaling End-to-End Models for Large-Scale Multilingual ASRcited by 61
  2. 2019Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentencescited by 55
  3. 2021Multilingual and code-switching ASR challenges for low resource Indian languagescited by 53
  4. 2021From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Textcited by 29
  5. 2022End-to-End Speech Translation for Code Switched Speechcited by 26
  6. 2022ASR2K: Speech Recognition for Around 2000 Languages without Audiocited by 26
  7. 2021Neural Inverse Text Normalizationcited by 20
  8. 2021Arabic Code-Switching Speech Recognition using Monolingual Datacited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 2.

8 papers.

  1. 2025Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and ASTcited by 60
  2. 2025Word Level Timestamp Generation for Automatic Speech Recognition and Translationcited by 6
  3. 2025UniCoM: A Universal Code-Switching Speech Generatorcited by 2
  4. 2024Romanization Encoding For Multilingual ASRcited by 1
  5. 2025Towards Fine-Grained Code-Switch Speech Translation with Semantic Space Alignmentcited by 1
  6. 2025WolBanking77: Wolof Banking Speech Intent Classification Datasetcited by 0
  7. 2026AfriSwitch: A Benchmark for In-the-Wild African Code-Switched Speech Recognitioncited by 0
  8. 2026Code-Switching Spoken Language Identification as Multi-Label Set Predictioncited by 0