Model Interpolation with Trans-dimensional Random Field Language Models for Speech Recognition
The dominant language models (LMs) such as n-gram and neural network (NN) models represent sentence probabilities in terms of conditionals. In contrast, a new trans-dimensional random field (TRF) LM has been recently introduced to show superior performances, where the whole sentence is modeled as a random field. In this paper, we examine how the TRF models can be interpolated with the NN models, and obtain 12.1\% and 17.9\% relative error rate reductions over 6-gram LMs for English and Chinese speech recognition respectively through log-linear combination.
Code (0)
등록된 구현이 없습니다.
Tasks
Sentencespeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Models
There has been a long recognition that discrete features (n-gram features) and neural network based features have complementary strengths for language models (LMs). Improved performance can be obtained by model interpola…
speech-recognitionSpeech RecognitionImproved training of neural trans-dimensional random field language models with dynamic noise-contrastive estimation
A new whole-sentence language model - neural trans-dimensional random field language model (neural TRF LM), where sentences are modeled as a collection of random fields, and the potential function is defined by a neural …
Language ModelingLanguage ModellingSentenceNeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation
Point Cloud Interpolation confronts challenges from point sparsity, complex spatiotemporal dynamics, and the difficulty of deriving complete 3D point clouds from sparse temporal information. This paper presents NeuroGaus…
Autonomous DrivingTrans-dimensional Random Fields for Language Modeling
PSF field learning based on Optimal Transport Distances
Context: in astronomy, observing large fractions of the sky within a reasonable amount of time implies using large field-of-view (fov) optical instruments that typically have a spatially varying Point Spread Function (PS…
AstronomyDimensionality Reduction