Towards continually learning new languages
Multilingual speech recognition with neural networks is often implemented with batch-learning, when all of the languages are available before training. An ability to add new languages after the prior training sessions can be economically beneficial, but the main challenge is catastrophic forgetting. In this work, we combine the qualities of weight factorization and elastic weight consolidation in order to counter catastrophic forgetting and facilitate learning new languages quickly. Such combination allowed us to eliminate catastrophic forgetting while still achieving performance for the new languages comparable with having all languages at once, in experiments of learning from an initial 10 languages to achieve 26 languages without catastrophic forgetting and a reasonable performance compared to training all languages from scratch.
Code (0)
등록된 구현이 없습니다.
Tasks
Allspeech-recognitionSpeech RecognitionTransfer LearningSimilar Papers 제목 키워드 기반
Continually Adding New Languages to Multilingual Language Models
Multilingual language models are trained on a fixed set of languages, and to support new languages, the models need to be retrained from scratch. This is an expensive endeavor and is often infeasible, as model developers…
Instruction FollowingTTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems
Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive. Subjective metrics such as Mean Opinion Score (MOS) are not easily comparable between works. Objective metrics are frequently used, but ra…
text-to-speechText to SpeechDesigning and Contextualising Probes for African Languages
Pretrained language models (PLMs) for African languages are continually improving, but the reasons behind these advances remain unclear. This paper presents the first systematic investigation into probing PLMs for lingui…
Active LearningSentenceCL-MASR: A Continual Learning Benchmark for Multilingual ASR
Modern multilingual automatic speech recognition (ASR) systems like Whisper have made it possible to transcribe audio in multiple languages with a single model. However, current state-of-the-art ASR models are typically …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Continual Learningspeech-recognition+1Cross-lingual Lifelong Learning
The longstanding goal of multi-lingual learning has been to develop a universal cross-lingual model that can withstand the changes in multi-lingual data distributions. However, most existing models assume full access to …
Continual LearningLifelong learningTransfer Learning