Adapting the adapters for code-switching in multilingual ASR
- URL: http://arxiv.org/abs/2310.07423v1
- Date: Wed, 11 Oct 2023 12:15:24 GMT
- Title: Adapting the adapters for code-switching in multilingual ASR
- Authors: Atharva Kulkarni, Ajinkya Kulkarni, Miguel Couceiro, Hanan Aldarmaki
- Abstract summary: Large pre-trained multilingual speech models have shown potential in scaling Automatic Speech Recognition to many low-resource languages.
Some of these models employ language adapters in their formulation, which helps to improve monolingual performance.
This formulation restricts the usability of these models on code-switched speech, where two languages are mixed together in the same utterance.
We propose ways to effectively fine-tune such models on code-switched speech, by assimilating information from both language adapters at each language adaptation point in the network.
- Score: 10.316724084739892
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Recently, large pre-trained multilingual speech models have shown potential
in scaling Automatic Speech Recognition (ASR) to many low-resource languages.
Some of these models employ language adapters in their formulation, which helps
to improve monolingual performance and avoids some of the drawbacks of
multi-lingual modeling on resource-rich languages. However, this formulation
restricts the usability of these models on code-switched speech, where two
languages are mixed together in the same utterance. In this work, we propose
ways to effectively fine-tune such models on code-switched speech, by
assimilating information from both language adapters at each language
adaptation point in the network. We also model code-switching as a sequence of
latent binary sequences that can be used to guide the flow of information from
each language adapter at the frame level. The proposed approaches are evaluated
on three code-switched datasets encompassing Arabic, Mandarin, and Hindi
languages paired with English, showing consistent improvements in
code-switching performance with at least 10\% absolute reduction in CER across
all test sets.
Related papers
- Streaming Bilingual End-to-End ASR model using Attention over Multiple
Softmax [6.386371634323785]
We propose a novel bilingual end-to-end (E2E) modeling approach, where a single neural model can recognize both languages.
The proposed model has shared encoder and prediction networks, with language-specific joint networks that are combined via a self-attention mechanism.
arXiv Detail & Related papers (2024-01-22T01:44:42Z) - Multilingual self-supervised speech representations improve the speech
recognition of low-resource African languages with codeswitching [65.74653592668743]
Finetuning self-supervised multilingual representations reduces absolute word error rates by up to 20%.
In circumstances with limited training data finetuning self-supervised representations is a better performing and viable solution.
arXiv Detail & Related papers (2023-11-25T17:05:21Z) - Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally.
Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
arXiv Detail & Related papers (2023-06-13T08:08:08Z) - Simple yet Effective Code-Switching Language Identification with
Multitask Pre-Training and Transfer Learning [0.7242530499990028]
Code-switching is the linguistics phenomenon where in casual settings, multilingual speakers mix words from different languages in one utterance.
We propose two novel approaches toward improving language identification accuracy on an English-Mandarin child-directed speech dataset.
Our best model achieves a balanced accuracy of 0.781 on a real English-Mandarin code-switching child-directed speech corpus and outperforms the previous baseline by 55.3%.
arXiv Detail & Related papers (2023-05-31T11:43:16Z) - Language-Universal Adapter Learning with Knowledge Distillation for
End-to-End Multilingual Speech Recognition [28.416831396722106]
We propose a language-universal adapter learning framework based on a pre-trained model for end-to-end multilingual automatic speech recognition.
An online knowledge distillation is then used to enable the language-universal adapters to learn both language-specific and universal features.
Compared to the conventional multilingual model, a 3.3% absolute error rate reduction is achieved.
arXiv Detail & Related papers (2023-02-28T14:43:49Z) - Language-Family Adapters for Low-Resource Multilingual Neural Machine
Translation [129.99918589405675]
Large multilingual models trained with self-supervision achieve state-of-the-art results in a wide range of natural language processing tasks.
Multilingual fine-tuning improves performance on low-resource languages but requires modifying the entire model and can be prohibitively expensive.
We propose training language-family adapters on top of mBART-50 to facilitate cross-lingual transfer.
arXiv Detail & Related papers (2022-09-30T05:02:42Z) - LAE: Language-Aware Encoder for Monolingual and Multilingual ASR [87.74794847245536]
A novel language-aware encoder (LAE) architecture is proposed to handle both situations by disentangling language-specific information.
Experiments conducted on Mandarin-English code-switched speech suggest that the proposed LAE is capable of discriminating different languages in frame-level.
arXiv Detail & Related papers (2022-06-05T04:03:12Z) - Code Switched and Code Mixed Speech Recognition for Indic languages [0.0]
Training multilingual automatic speech recognition (ASR) systems is challenging because acoustic and lexical information is typically language specific.
We compare the performance of end to end multilingual speech recognition system to the performance of monolingual models conditioned on language identification (LID)
We also propose a similar technique to solve the Code Switched problem and achieve a WER of 21.77 and 28.27 over Hindi-English and Bengali-English respectively.
arXiv Detail & Related papers (2022-03-30T18:09:28Z) - Efficient Test Time Adapter Ensembling for Low-resource Language
Varieties [115.12997212870962]
Specialized language and task adapters have been proposed to facilitate cross-lingual transfer of multilingual pretrained models.
An intuitive solution is to use a related language adapter for the new language variety, but we observe that this solution can lead to sub-optimal performance.
In this paper, we aim to improve the robustness of language adapters to uncovered languages without training new adapters.
arXiv Detail & Related papers (2021-09-10T13:44:46Z) - Are Multilingual Models Effective in Code-Switching? [57.78477547424949]
We study the effectiveness of multilingual language models to understand their capability and adaptability to the mixed-language setting.
Our findings suggest that pre-trained multilingual models do not necessarily guarantee high-quality representations on code-switching.
arXiv Detail & Related papers (2021-03-24T16:20:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.