paper-with-me

홈 › Papers

Label-Context-Dependent Internal Language Model Estimation for CTC

2025-06-06 · Zijian Yang, Minh-Nghia Phan, Ralf Schlüter, Hermann Ney

Although connectionist temporal classification (CTC) has the label context independence assumption, it can still implicitly learn a context-dependent internal language model (ILM) due to modern powerful encoders. In this work, we investigate the implicit context dependency modeled in the ILM of CTC. To this end, we propose novel context-dependent ILM estimation methods for CTC based on knowledge distillation (KD) with theoretical justifications. Furthermore, we introduce two regularization methods for KD. We conduct experiments on Librispeech and TED-LIUM Release 2 datasets for in-domain and cross-domain evaluation, respectively. Experimental results show that context-dependent ILMs outperform the context-independent priors in cross-domain evaluation, indicating that CTC learns a context-dependent ILM. The proposed label-level KD with smoothing method surpasses other ILM estimation approaches, with more than 13% relative improvement in word error rate compared to shallow fusion.

📄 PDF Abstract BibTeX arXiv:2506.06096

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationLanguage ModelingLanguage Modelling

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

Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASR

2022-01-26 · Yufei Liu, Rao Ma, HaiHua Xu, Yi He 외

An end-to-end (E2E) ASR model implicitly learns a prior Internal Language Model (ILM) from the training transcripts. To fuse an external LM using Bayes posterior theory, the log likelihood produced by the ILM has to be a…

DecoderLanguage ModelingLanguage ModellingSpeech Recognition

Plug-and-Play Performance Estimation for LLM Services without Relying on Labeled Data

2024-10-10 · Can Wang, Dianbo Sui, Hongliang Sun, Hao Ding 외

Large Language Model (LLM) services exhibit impressive capability on unlearned tasks leveraging only a few examples by in-context learning (ICL). However, the success of ICL varies depending on the task and context, lead…

In-Context LearningLanguage ModelingLanguage ModellingLarge Language Model

Perturbation-based QE: An Explainable, Unsupervised Word-level Quality Estimation Method for Blackbox Machine Translation

2023-05-12 · Tu Anh Dinh, Jan Niehues

Quality Estimation (QE) is the task of predicting the quality of Machine Translation (MT) system output, without using any gold-standard translation references. State-of-the-art QE models are supervised: they require hum…

Machine TranslationTranslationWord Sense Disambiguation

Librispeech Transducer Model with Internal Language Model Prior Correction

2021-04-07 · Albert Zeyer, André Merboldt, Wilfried Michel, Ralf Schlüter 외

We present our transducer model on Librispeech. We study variants to include an external language model (LM) with shallow fusion and subtract an estimated internal LM. This is justified by a Bayesian interpretation where…

Language ModelingLanguage ModellingmodelSentence+1

Learning by Distilling Context

2022-09-30 · Charlie Snell, Dan Klein, Ruiqi Zhong

Language models significantly benefit from context tokens, such as prompts or scratchpads. They perform better when prompted with informative instructions, and they acquire new reasoning capabilities by generating a scra…

Language ModellingText to SQLText-To-SQL