paper-with-me

Papers

Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach

2021-10-20 · Mun-Hak Lee, Joon-Hyuk Chang

The remarkable performance of the pre-trained language model (LM) using self-supervised learning has led to a major paradigm shift in the study of natural language processing. In line with these changes, leveraging the performance of speech recognition systems with massive deep learning-based LMs is a major topic of speech recognition research. Among the various methods of applying LMs to speech recognition systems, in this paper, we focus on a cross-modal knowledge distillation method that transfers knowledge between two types of deep neural networks with different modalities. We propose an acoustic model structure with multiple auxiliary output layers for cross-modal distillation and demonstrate that the proposed method effectively compensates for the shortcomings of the existing label-interpolation-based distillation method. In addition, we extend the proposed method to a hierarchical distillation method using LMs trained in different units (senones, monophones, and subwords) and reveal the effectiveness of the hierarchical distillation method through an ablation study.

📄 PDF Abstract BibTeX arXiv:2110.10429

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationLanguage ModelingLanguage ModellingmodelMulti-Task LearningSelf-Supervised Learningspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation

2023-01-30 · Minglun Han, Feilong Chen, Jing Shi, Shuang Xu 외

Large-scale pre-trained language models (PLMs) have shown great potential in natural language processing tasks. Leveraging the capabilities of PLMs to enhance automatic speech recognition (ASR) systems has also emerged a…

Automatic Speech RecognitionKnowledge DistillationLanguage Modellingspeech-recognition+2

Decoupled Hierarchical Distillation for Multimodal Emotion Recognition

2026-02-04 · Yong Li, Yuanzhi Wang, Yi Ding, Shiqing Zhang 외 arxiv

Human multimodal emotion recognition (MER) seeks to infer human emotions by integrating information from language, visual, and acoustic modalities. Although existing MER approaches have achieved promising results, they s…

Multimodal Emotion RecognitionKnowledge Distillation

Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification

2021-08-05 · Yidi Jiang, Bidisha Sharma, Maulik Madhavi, Haizhou Li

End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Classificationintent-classification+7

Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR

2026-08-04 · Yuan Xie, Jiaqi Song, Xianliang Wang, Ming Lei 외 arxiv

Modern LLM-based ASR systems have established multilingual capability as a standard feature, leveraging large-scale multilingual corpora and LLMs' cross-lingual knowledge to achieve competitive performance across multili…

Reinforcement Learning

HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression

2021-10-16 · EMNLP 2021 11 · Chenhe Dong, Yaliang Li, Ying Shen, Minghui Qiu

On many natural language processing tasks, large pre-trained language models (PLMs) have shown overwhelming performances compared with traditional neural network methods. Nevertheless, their huge model size and low infer…

Few-Shot LearningKnowledge DistillationLanguage ModelingLanguage Modelling+2