Every reference with a DOI in the deposited reference list resolved to a known
work in Crossref or DataCite at the dated check, and none carried a retraction,
withdrawal, or removal notice.
The 43 references without a DOI — listed, not checked
no DOI — not checkedref1
no DOI — not checkedngram-1) 13: if ? node ๏ฟฝ๐ ? ๐ ๐ .expanded nodes such that ๏ฟฝ๐ .hist = hist then 14: ๏ฟฝ๐ ? ๐ ๐ .Duplicate(๏ฟฝ ๐ , ๏ฟฝ๐ ) ? Create arc between expanded nodes 15: else 16: ๏ฟฝ๐ ? ๐ ๐ .Duplicate(hist) ? Create expanded node with new history 17: ๐ ๐ .expanded nodes.Append(๏ฟฝ ๐ ) 18: ๏ฟฝ๐ ? ๐ ๐ .Duplicate(๏ฟฝ ๐ , ๏ฟฝ๐ ) ? Create arc between expanded nodes 19: end if 20: post ? LastNItems([cache.GetPost(๏ฟฝ ๐ .hist, ๏ฟฝ ๐ .time), ๏ฟฝ๐ .post], ngram-1) 21: if cache
no DOI — not checkedref4
no DOI — not checkedConnectionist speech recognition: a hybrid approach
no DOI — not checkedThe AMI meeting corpus: A pre-announcement
no DOI — not checkedListen, attend and spell: A neural network for large vocabulary conversational speech recognition
no DOI — not checkedState-of-the-art speech recognition with sequenceto-sequence models
no DOI — not checkedAttention-based models for speech recognition
no DOI — not checkedref13
no DOI — not checkedPosterior probability decoding, confidence estimation and system combination
no DOI — not checkedA post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)
no DOI — not checkedSequence transduction with recurrent neural networks
no DOI — not checkedConnectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks
no DOI — not checkedConformer: Convolution-augmented Transformer for speech recognition
no DOI — not checkedEnd-to-end speech recognition using lattice-free MMI
no DOI — not checkedTraining language models for long-span cross-sentence evaluation
no DOI — not checkedref24
no DOI — not checkedLattice-free state-level minimum Bayes risk training of acoustic models
no DOI — not checkedTransformers are RNNs: Fast autoregressive Transformers with linear attention
no DOI — not checkedCumulative adaptation for BLSTM acoustic models
no DOI — not checkedSubword regularization: Improving neural network translation models with multiple subword candidates
no DOI — not checkedAn overview on automatic speech attribute transcription (ASAT)
no DOI — not checkedIntegrating source-channel and attention-based sequence-to-sequence models for speech recognition
no DOI — not checkedStreaming automatic speech recognition with the Transformer model
no DOI — not checkedTools for the analysis of benchmark speech recognition tests
no DOI — not checkedSpecAugment: A simple data augmentation method for automatic speech recognition
no DOI — not checkedSemi-orthogonal low-rank matrix factorization for deep neural networks
no DOI — not checkedThe Kaldi speech recognition toolkit
no DOI — not checkedLess is more: Improved RNN-T decoding using limited label context and path merging
no DOI — not checkedTwo-pass end-to-end speech recognition
no DOI — not checkedAdvancing RNN transducer technology for speech recognition
no DOI — not checkedError back propagation for sequence training of context-dependent deep networks for conversational speech transcription
no DOI — not checkedTransformer language models with LSTM-based cross-utterance information representation
no DOI — not checkedSingle headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard-300
no DOI — not checkedOn the limit of English conversational speech recognition
no DOI — not checkedHybrid autoregressive transducer (HAT)
no DOI — not checkedAttention is all you need
no DOI — not checkedref52
no DOI — not checkedAn investigation of phone-based subword units for end-to-end speech recognition
no DOI — not checkedESPnet: End-to-end speech processing toolkit
no DOI — not checkedCombination of end-to-end and hybrid models for speech recognition
no DOI — not checkedImproved training of endto-end attention models for speech recognition
no DOI — not checkedA segmental CRF approach to large vocabulary continuous speech recognition
checked 2026-09-10 — re-checked daily as this page is visited;
titles and statuses come from Crossref and DataCite and are not part of the signed record
Both snippets point at the live badge image and link back to this page. The
badge re-renders from the daily check, so an embed never goes stale by more than a day of visits.