MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition
Multi-lingual speech recognition aims to distinguish linguistic expressions in different languages and integrate acoustic processing simultaneously. In contrast, current multi-lingual speech recognition research follows a language-aware paradigm, mainly targeted to improve recognition performance rather than discriminate language characteristics. In this paper, we present a multi-lingual speech recognition network named Mixture-of-Language-Expert(MoLE), which digests speech in a variety of languages. Specifically, MoLE analyzes linguistic expression from input speech in arbitrary languages, activating a language-specific expert with a lightweight language tokenizer. The tokenizer not only activates experts, but also estimates the reliability of the activation. Based on the reliability, the activated expert and the language-agnostic expert are aggregated to represent language-conditioned embedding for efficient speech recognition. Our proposed model is evaluated in 5 languages scenario, and the experimental results show that our structure is advantageous on multi-lingual recognition, especially for speech in low-resource language.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism
While Large Language Models (LLMs) are commonly fine-tuned to handle domain-specific tasks before being applied to vertical applications, adapting them to complex scenarios with diverse specialized knowledge remains chal…
parameter-efficient fine-tuningUnderstanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steering
Mixture-of-Experts (MoE) architectures have shown strong multilingual capabilities, yet the internal mechanisms underlying performance gains and cross-language differences remain insufficiently understood. In this work, …
MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models
Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks…
AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts
We introduce AdaMoLE, a novel method for fine-tuning large language models (LLMs) through an Adaptive Mixture of Low-Rank Adaptation (LoRA) Experts. Moving beyond conventional methods that employ a static top-k strategy …
Multiple Choice Question Answering (MCQA)LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting
Recent research has shown that large language models (LLMs) can be effectively used for real-world time series forecasting due to their strong natural language understanding capabilities. However, aligning time series in…
Computational EfficiencyNatural Language UnderstandingTime SeriesTime Series Forecasting+1