paper-with-me

홈 › Papers

Distilling Knowledge Using Parallel Data for Far-field Speech Recognition

2018-02-20 · Jiangyan Yi, Jian-Hua Tao, Zhengqi Wen, Bin Liu

In order to improve the performance for far-field speech recognition, this paper proposes to distill knowledge from the close-talking model to the far-field model using parallel data. The close-talking model is called the teacher model. The far-field model is called the student model. The student model is trained to imitate the output distributions of the teacher model. This constraint can be realized by minimizing the Kullback-Leibler (KL) divergence between the output distribution of the student model and the teacher model. Experimental results on AMI corpus show that the best student model achieves up to 4.7% absolute word error rate (WER) reduction when compared with the conventionally-trained baseline models.

📄 PDF Abstract BibTeX arXiv:1802.06941

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers

2019-11-26 · Ya Zhao, Rui Xu, Xinchao Wang, Peng Hou 외

Lip reading has witnessed unparalleled development in recent years thanks to deep learning and the availability of large-scale datasets. Despite the encouraging results achieved, the performance of lip reading, unfortuna…

Knowledge DistillationLipreadingLip Readingspeech-recognition+1

Distilling HuBERT with LSTMs via Decoupled Knowledge Distillation

2023-09-18 · Danilo de Oliveira, Timo Gerkmann

Much research effort is being applied to the task of compressing the knowledge of self-supervised models, which are powerful, yet large and memory consuming. In this work, we show that the original method of knowledge di…

Automatic Speech RecognitionKnowledge Distillationspeech-recognitionSpeech Recognition

Distilling a Pretrained Language Model to a Multilingual ASR Model

2022-06-25 · Kwanghee Choi, Hyung-Min Park

Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yielding a more useful general language model.…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+3

A Comprehensive Survey on Knowledge Distillation of Diffusion Models

2023-04-09 · Weijian Luo

Diffusion Models (DMs), also referred to as score-based diffusion models, utilize neural networks to specify score functions. Unlike most other probabilistic models, DMs directly model the score functions, which makes th…

Knowledge DistillationSurvey

Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts

2025-08-18 · Duygu Altinok arxiv

ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach tha…