Computer Speech and Language

Papers
(The H4-Index of Computer Speech and Language is 24. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2021-02-01 to 2025-02-01.)
ArticleCitations
Non-negative matrix factorization-based time-frequency feature extraction of voice signal for Parkinson's disease prediction141
Building a text retrieval system for the Sanskrit language: Exploring indexing, stemming, and searching issues99
Editorial Board82
Speech enhancement approach for body-conducted unvoiced speech based on Taylor–Boltzmann machines trained DNN82
A new speech corpus of super-elderly Japanese for acoustic modeling81
Editorial Board63
Adaptive line enhancer for nonstationary harmonic noise reduction54
Sentence transition matrix: An efficient approach that preserves sentence semantics51
Effective infant cry signal analysis and reasoning using IARO based leaky Bi-LSTM model46
KddRES: A Multi-level Knowledge-driven Dialogue Dataset for Restaurant Towards Customized Dialogue System46
Learning to extract from multiple perspectives for neural keyphrase extraction43
RepSum: A general abstractive summarization framework with dynamic word embedding representation correction43
GEPC: Global embeddings with PID control39
Automatic detection of pharyngeal fricatives in cleft palate speech using acoustic features based on the vocal tract area spectrum38
Editorial Board37
Two evaluations on Ontology-style relation annotations36
Talking-heads attention-based knowledge representation for link prediction34
PLDA inspired Siamese networks for speaker verification31
On the use of blind channel response estimation and a residual neural network to detect physical access attacks to speaker verification systems29
Transfer fine-tuning of BERT with phrasal paraphrases27
Automatic offline annotation of turn-taking transitions in task-oriented dialogue27
Stochastic Data-to-Text Generation Using Syntactic Dependency Information25
A benchmark dataset for Turkish data-to-text generation25
Neural candidate-aware language models for speech recognition24
0.081688165664673