Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter
Multilingual intelligent assistants, such as ChatGPT, have recently gained popularity. To further expand the applications of multilingual artificial intelligence assistants and facilitate international communication, it is essential to enhance the performance of multilingual speech recognition, which is a crucial component of speech interaction. In this paper, we propose two simple and parameter-efficient methods: language prompt tuning and frame-level language adapter, to respectively enhance language-configurable and language-agnostic multilingual speech recognition. Additionally, we explore the feasibility of integrating these two approaches using parameter-efficient fine-tuning methods. Our experiments demonstrate significant performance improvements across seven languages using our proposed methods.
Code (0)
등록된 구현이 없습니다.
Tasks
parameter-efficient fine-tuningspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
The Eloquence team submission for task 1 of MLC-SLM challenge
In this paper, we present our studies and experiments carried out for the task 1 of the Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM), which focuses on advancing multilingual conve…
Contrastive LearningSpeech RecognitionILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition
The deep integration of large language models and automatic speech recognition systems has become a promising research direction with high practical value. To address the overfitting issue commonly observed in Low-Rank A…
Speech RecognitionSpeech SeparationEnhancing Multilingual Speech Generation and Recognition Abilities in LLMs with Constructed Code-switched Data
While large language models (LLMs) have been explored in the speech domain for both generation and recognition tasks, their applications are predominantly confined to the monolingual scenario, with limited exploration in…
Speech SynthesisIdeal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text
Integrating audio encoders with LLMs through connectors has enabled these models to process and comprehend audio modalities, significantly enhancing speech-to-text tasks, including automatic speech recognition (ASR) and …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)automatic-speech-translationspeech-recognition+2Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition
Low-resource speech recognition has been long-suffering from insufficient training data. In this paper, we propose an approach that leverages neighboring languages to improve low-resource scenario performance, founded on…
speech-recognitionSpeech Recognition