Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition
We aim to improve the robustness of Automatic Speech Recognition (ASR) systems against non-native speech, particularly in low-resourced multi-accent settings. We introduce Mixture of Accent-Specific LoRAs (MAS-LoRA), a fine-tuning method that leverages a mixture of Low-Rank Adaptation (LoRA) experts, each specialized in a specific accent. This method can be used when the accent is known or unknown at inference time, without the need to fine-tune the model again. Our experiments, conducted using Whisper on the L2-ARCTIC corpus, demonstrate significant improvements in Word Error Rate compared to regular LoRA and full fine-tuning when the accent is unknown. When the accent is known, the results further improve. Furthermore, MAS-LoRA shows less catastrophic forgetting than the other fine-tuning methods. To the best of our knowledge, this is the first use of a mixture of LoRA experts for non-native multi-accent ASR.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition
Accented speech remains a persistent challenge for automatic speech recognition (ASR), as most models are trained on data dominated by a few high-resource English varieties, leading to substantial performance degradation…
Accented Speech RecognitionSpeechMoE2: Mixture-of-Experts Model with Improved Routing
Mixture-of-experts based acoustic models with dynamic routing mechanisms have proved promising results for speech recognition. The design principle of router architecture is important for the large model capacity and hig…
Computational EfficiencyMixture-of-Expertsmodelspeech-recognition+1MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning
Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have significantly improved the adaptation of LLMs to downstream tasks in a resource-efficient manner. However, in multi-task scenarios, challenges such as trainin…
Computational EfficiencyMixture-of-ExpertsMulti-Task Learningparameter-efficient fine-tuningCombining Pretrained High-Resource Embeddings and Subword Representations for Low-Resource Languages
The contrast between the need for large amounts of data for current Natural Language Processing (NLP) techniques, and the lack thereof, is accentuated in the case of African languages, most of which are considered low-re…
TranslationWord EmbeddingsHow Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing?
Cross-lingual Entity Typing (CLET) aims at improving the quality of entity type prediction by transferring semantic knowledge learned from rich-resourced languages to low-resourced languages. In this paper, by utilizing …
Entity TypingMixture-of-ExpertsTransfer LearningType prediction