paper-with-me

홈 › Papers

Efficient Speech Translation through Model Compression and Knowledge Distillation

2025-05-26 · Yasmin Moslem

Efficient deployment of large audio-language models for speech translation remains challenging due to their significant computational requirements. In this paper, we address this challenge through our system submissions to the "Model Compression" track at the International Conference on Spoken Language Translation (IWSLT 2025). We experiment with a combination of approaches including iterative layer pruning based on layer importance evaluation, low-rank adaptation with 4-bit quantization (QLoRA), and knowledge distillation. In our experiments, we use Qwen2-Audio-7B-Instruct for speech translation into German and Chinese. Our pruned (student) models achieve up to a 50% reduction in both model parameters and storage footprint, while retaining 97-100% of the translation quality of the in-domain (teacher) models.

📄 PDF Abstract BibTeX arXiv:2505.20237

Code (1)

ymoslem/model-compression 공식 구현 pytorch

Tasks

Knowledge DistillationModel CompressionQuantizationTranslation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders

2023-09-14 · Heng-Jui Chang, Ning Dong, Ruslan Mavlyutov, Sravya Popuri 외

Large-scale self-supervised pre-trained speech encoders outperform conventional approaches in speech recognition and translation tasks. Due to the high cost of developing these large models, building new encoders for new…

Contrastive LearningKnowledge DistillationModel Compressionspeech-recognition+4

End-to-End Speech Translation with Knowledge Distillation

2019-04-17 · Yuchen Liu, Hao Xiong, Zhongjun He, Jiajun Zhang 외

End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years. Compared to conventional pipeline systems, end-to-e…

Knowledge Distillationspeech-recognitionSpeech RecognitionTranslation

Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation

2025-08-15 · Chenyang Le, Yinfeng Xia, Huiyan Li, Manhong Wang 외 arxiv

Recent advancements in speech-to-text translation have led to the development of multilingual models capable of handling multiple language pairs simultaneously. However, these unified models often suffer from large param…

Speech-to-Text TranslationKnowledge DistillationModel Compression

On Knowledge Distillation for Direct Speech Translation

2020-12-09 · Marco Gaido, Mattia A. Di Gangi, Matteo Negri, Marco Turchi

Direct speech translation (ST) has shown to be a complex task requiring knowledge transfer from its sub-tasks: automatic speech recognition (ASR) and machine translation (MT). For MT, one of the most promising techniques…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Knowledge DistillationMachine Translation+4

SimulSpeech: End-to-End Simultaneous Speech to Text Translation

2020-07-01 · ACL 2020 6 · Yi Ren, Jinglin Liu, Xu Tan, Chen Zhang 외

In this work, we develop SimulSpeech, an end-to-end simultaneous speech to text translation system which translates speech in source language to text in target language concurrently. SimulSpeech consists of a speech enco…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderKnowledge Distillation+9