No article text was recorded for this version.
perplexity-performance gap
Version 1 of 1101 papers122 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Methods for combining language models in speech recognition
- Blog: Investigating the relationship between language model perplexity and IR precision-recall measures
- Blog: Character-Aware Sub-Word Level Language Modeling for Uyghur and Turkish ASR
- Blog: Label-Context-Dependent Internal Language Model Estimation for CTC
- Blog: Review of statistical modeling of highly inflected lithuanian using very large vocabulary
- Blog: Large Margin Neural Language Model
- Blog: Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition
- Blog: Improving unsupervised language model adaptation with discriminative data filtering
- Blog: Improving End-to-End Speech Recognition with Policy Learning
- Blog: Investigations on discriminative training in large scale acoustic model estimation
- Blog: A Comparison between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition
- Blog: Improving Language Modeling with an Adversarial Critic for Automatic Speech Recognition
- Blog: Investigating the relationship between language model perplexity and IR precision-recall measures
- Blog: Dependency Recurrent Neural Language Models for Sentence Completion
- Blog: Improving language modeling by combining heteogeneous corpora
- Blog: Enhancing exemplar-based posteriors for speech recognition tasks
- Blog: Maximum accept and reject (MARS) training of HMM-GMM speech recognition systems
- Blog: Minimum boundary error training for automatic phonetic segmentation
- Blog: OS-Denseformer: A Lightweight End-to-End Noise-Robust Method for Chinese Speech Recognition
- Blog: On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer
- Blog: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation
- Blog: A hierarchical F0 modeling method for HMM-based speech synthesis
- Blog: Combination of random indexing based language model and n-gram language model for speech recognition
- Blog: Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models
- Blog: Towards Recurrent Neural Networks Language Models with Linguistic and Contextual Features
- Blog: Neural network language models for conversational speech recognition
- Blog: A fast online algorithm for large margin training of continuous density hidden Markov models
- Blog: A Hybrid Morphologically Decomposed Factored Language Models for Arabic LVCSR
- Blog: Scalable Data Ablation Approximations for Language Models through Modular Training and Merging
- Blog: Cache-Augmented Latent Topic Language Models for Speech Retrieval
- Blog: An approach to measuring the performance of Automatic Speech Recognition(ASR) models in the context of Large Language Model(LLM) powered applications
- Blog: Minimum word error based discriminative training of language models
- Blog: Relative error bounds for statistical classifiers based on the f-divergence
- Blog: Morpheme based factored language models for German LVCSR
- Blog: Intonational Boundaries, Speech Repairs and Discourse Markers: Modeling Spoken Dialog
- Blog: A comparison of training approaches for discriminative segmental models
- Blog: Phrasal cohort based unsupervised discriminative language modeling
- Blog: Transcription-less call routing using unsupervised language model adaptation
- Blog: Context dependent language model adaptation
- Blog: Trigger-based language model adaptation for automatic meeting transcription
- Blog: The BBN Spoken Language System
- Blog: Correction Focused Language Model Training for Speech Recognition
- Blog: Marco-ASR: A Principled and Metric-Driven Framework for Fine-Tuning Large-Scale ASR Models for Domain Adaptation
- Blog: Learning Domain Specific Language Models for Automatic Speech Recognition through Machine Translation
- Blog: Discriminative maximum entropy language model for speech recognition
- Blog: Speech Recognition Rescoring with Large Speech-Text Foundation Models
- Blog: Scalable language model adaptation for spoken dialogue systems
- Blog: Discriminative Pruning of Language Models for Chinese Word Segmentation
- Blog: Measuring the Confusability of Pronunciations in Speech Recognition
- Blog: Toward a Better Understanding of Deep Neural Network Based Acoustic Modelling: An Empirical Investigation
- Blog: Feature combination approaches for discriminative language models
- Blog: Implicit state-tying for support vector machines based speech recognition
- Blog: Log-Linear System Combination Using Structured Support Vector Machines
- Blog: Integrating Lattice-Free MMI Into End-to-End Speech Recognition
- Blog: A posteriori multiple word-domain language model
- Blog: O-1: Self-training with Oracle and 1-best Hypothesis
- Blog: Improving cross-domain n-gram language modelling with skipgrams
- Blog: A Comparison of Criteria for Maximum Entropy/ Minimum Divergence Feature Selection
- Blog: (Dynamic) Prompting might be all you need to repair Compressed LLMs
- Blog: The philips/RWTH system for transcription of broadcast news
Showing 60 of 101 papers.
History & citation
Current · Permanent link
- The Perplexity Performance Gap in Speech Recognition merged into this direction (82% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_perplexity_performance_gap_4013c29f,
title = {perplexity-performance gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/perplexity-performance-gap/rdr_4013c29f0a6840f1905cda3ac469bfa2},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_perplexity_performance_gap_4013c29f_v1,
title = {perplexity-performance gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/perplexity-performance-gap/rdr_4013c29f0a6840f1905cda3ac469bfa2/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}