Multilingual Speech Recognition using Knowledge Transfer across Learning Processes
Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim to enhance the multilingual ASR performance in two ways, 1)studying the impact of feeding a one-hot vector identifying the language, 2)formulating the task with a meta-learning objective combined with self-supervised learning (SSL). We associate every language with a distinct task manifold and attempt to improve the performance by transferring knowledge across learning processes itself as compared to transferring through final model parameters. We employ this strategy on a dataset comprising of 6 languages for an in-domain ASR task, by minimizing an objective related to expected gradient path length. Experimental results reveal the best pre-training strategy resulting in 3.55% relative reduction in overall WER. A combination of LEAP and SSL yields 3.51% relative reduction in overall WER when using language ID.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Meta-LearningSelf-Supervised Learningspeech-recognitionSpeech RecognitionTransfer LearningSimilar Papers 제목 키워드 기반
CLARA: Multilingual Contrastive Learning for Audio Representation Acquisition
Multilingual speech processing requires understanding emotions, a task made difficult by limited labelled data. CLARA, minimizes reliance on labelled data, enhancing generalization across languages. It excels at fosterin…
Audio ClassificationContrastive LearningCross-Lingual TransferData Augmentation+6When More is not Necessary Better: Multilingual Auxiliary Tasks for Zero-Shot Cross-Lingual Transfer of Hate Speech Detection Models
Zero-shot cross-lingual transfer learning has been shown to be highly challenging for tasks involving a lot of linguistic specificities or when a cultural gap is present between languages, such as in hate speech detectio…
Cross-Lingual TransferHate Speech DetectionLanguage ModelingLanguage Modelling+6Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models
Zero-shot cross-lingual transfer learning has been shown to be highly challenging for tasks involving a lot of linguistic specificities or when a cultural gap is present between languages, such as in hate speech detectio…
Cross-Lingual TransferHate Speech Detectionnamed-entity-recognitionNamed Entity Recognition+4A Survey of Multilingual Models for Automatic Speech Recognition
Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world's languages do not have usable systems due to the lack of large speech datasets to t…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Cross-Lingual TransferSelf-Supervised Learning+4Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages
This work introduces Zambezi Voice, an open-source multilingual speech resource for Zambian languages. It contains two collections of datasets: unlabelled audio recordings of radio news and talk shows programs (160 hours…
Cross-Lingual Transferspeech-recognitionSpeech RecognitionTransfer Learning