Challenge: Pre-training on high-resource automatic speech recognition (ASR) tasks improves ST performance even when source language is low-resourced.
Approach: They propose a method to improve direct speech-to-text translation when source language is low-resource . they pre-train model on high-res automatic speech recognition task and fine-tune parameters for ST .
Outcome: The proposed approach improves Spanish English ST even when the source language is low-resource . the pre-trained encoder accounts for most of the improvement, the authors show .

Similar Papers

Unveiling the Role of Pretraining in Direct Speech Translation (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to train direct speech-to-text translation systems are pretraining the encoder on automatic speech recognition, thus losing efficiency in the training process.
Approach: They propose to change the decoder cross-attention to integrate source information from earlier steps in training.
Outcome: The proposed model can achieve comparable performance to the pretrained model while reducing training time.
Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation (2023.acl-long)

Copied to clipboard

Challenge: Using self-training or text-to-speech (TTS) to improve low-resource ASR performance is costly and can lead to catastrophic forgetting.
Approach: They examine whether data augmentation techniques could help improve low-resource ASR performance . they use self-training to generate transcriptions, which are combined with original data to train new system .
Outcome: The proposed approach yields a 20.5% reduction in WER compared to a system trained on 24 minutes of manually transcribed speech.
Pretraining Language Models Using Translationese (2024.emnlp-main)

Copied to clipboard

Challenge: a recent study shows that large language models perform well in low-resource languages . a vast majority of languages don't have comparable data as compared to English .
Approach: They propose to use Translationese as synthetic data for pre-training language models for low-resource languages.
Outcome: The proposed method reduces performance of LMs trained on clean data in Indian languages . the proposed model performs better in English than in other languages, but is not comparable to English.
Curriculum Pre-training for End-to-End Speech Translation (2020.acl-main)

Copied to clipboard

Challenge: End-to-end speech translation requires a powerful encoder to transcribe, understand and learn cross-lingual semantics simultaneously.
Approach: They propose a curriculum pre-training method that includes an elementary course for transcription learning and two advanced courses for understanding the utterance and mapping words in two languages.
Outcome: The proposed method improves on En-De and En-Fr speech translation benchmarks.
An (unhelpful) guide to selecting the best ASR architecture for your under-resourced language (2023.acl-short)

Copied to clipboard

Challenge: English ASR now has word error rates comparable to that of human transcriptionists, but only for the handful of the world's 7000 languages with abundant training resources.
Approach: They propose to use four of the most popular ASR toolkits to train ASR models for eleven languages with limited ASR training resources: eleven widely spoken languages of Africa, Asia, and South America, one endangered language of Central America, and three critically endangered languages of North America.
Outcome: The proposed architecture outperforms four of the most popular ASR toolkits for eleven languages with limited training resources.
Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for pre-training for automatic speech recognition (ASR) focus on single-stage pre-train followed by fine-tuning on downstream task.
Approach: They propose a multi-modal pre-training method that combines unsupervised pre-training with translation-based supervised mid-training.
Outcome: The proposed method improves WERs by 38.45% over baselines on both Librispeech and SUPERB.
A Survey of Multilingual Models for Automatic Speech Recognition (2022.lrec-1)

Copied to clipboard

Challenge: Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, but the majority of the world’s languages do not have usable systems due to the lack of large speech datasets to train these models.
Approach: They propose to use unlabeled speech data to build multilingual ASR models that can be used for improved performance on low-resource languages.
Outcome: The proposed models can be used to improve performance on low-resource languages by using unlabeled speech data.
Pre-training via Leveraging Assisting Languages for Neural Machine Translation (2020.acl-srw)

Copied to clipboard

Challenge: Sequence-to-sequence (S2S) pre-training with large monolingual data is not always available for the languages of interest (LOI).
Approach: They propose to use monolingual corpora of other languages to complement the scarce monolingual LOI by script mapping (Chinese to Japanese) . Using only Chinese and French monolinguals, they improve Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios.
Outcome: The proposed approach improves Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios.
Improving Low-Resource Languages in Pre-Trained Multilingual Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Pre-trained multilingual language models are the foundation of many NLP approaches, but are often not well-supported by these models due to small available monolingual corpora.
Approach: They propose an unsupervised approach to improve cross-lingual representations of low-resource languages by bootstrapping word translation pairs from monolingual corpora and using them to improve language alignment.
Outcome: The proposed approach improves cross-lingual representations on low-resource languages using word retrieval and zero-shot named entity recognition.
Disentangling Pretrained Representation to Leverage Low-Resource Languages in Multilingual Machine Translation (2024.lrec-main)

Copied to clipboard

Challenge: Multilingual neural machine translation requires an enormous dataset, leaving the low-resource language (LRL) underdeveloped.
Approach: They evaluated five languages using a parallel corpus of 1,000 instances each and found a zero-shot improvement of 7.4 from the baseline score of 7.1 to a score of 15.5 at best.
Outcome: The proposed model improves performance in the linguistically diverse country of Indonesia by 7.4 from baseline score of 7.1 to 15.5 at best.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations