Computer Speech and Language

Papers
(The median citation count of Computer Speech and Language is 3. 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 2021-08-01 to 2025-08-01.)
ArticleCitations
A language-agnostic model of child language acquisition201
Stochastic Data-to-Text Generation Using Syntactic Dependency Information106
Corpus and unsupervised benchmark: Towards Tagalog grammatical error correction105
Room impulse response reshaping-based expectation–maximization in an underdetermined reverberant environment70
Speech enhancement approach for body-conducted unvoiced speech based on Taylor–Boltzmann machines trained DNN64
Seq2Seq dynamic planning network for progressive text generation64
KddRES: A Multi-level Knowledge-driven Dialogue Dataset for Restaurant Towards Customized Dialogue System62
Automatic detection of behavioural codes in team interactions62
Identifying offensive memes in low-resource languages: A multi-modal multi-task approach using valence and arousal56
Editorial Board55
A method of phonemic annotation for Chinese dialects based on a deep learning model with adaptive temporal attention and a feature disentangling structure54
Monotonic Gaussian regularization of attention for robust automatic speech recognition53
Contextual emotion detection using ensemble deep learning46
Complementary regional energy features for spoofed speech detection45
Multi-branch feature aggregation based on multiple weighting for speaker verification41
PaSCoNT - Parallel Speech Corpus of Northern-central Thai for automatic speech recognition41
Unsupervised question-retrieval approach based on topic keywords filtering and multi-task learning38
Improving low-resource machine transliteration by using 3-way transfer learning33
Misogynistic attitude detection in YouTube comments and replies: A high-quality dataset and algorithmic models32
Editorial Board29
Unsupervised sign language validation process based on hand-motion parameter clustering27
Perceptions and reactions to conversational privacy initiated by a conversational user interface27
Maximal activation weighted memory for aspect based sentiment analysis27
Editorial Board27
Augmentative and alternative speech communication (AASC) aid for people with dysarthria26
Adversarial subsequences for unconditional text generation25
Enhancing analysis of diadochokinetic speech using deep neural networks24
A hybrid approach to Natural Language Inference for the SICK dataset24
Exploring accidental triggers of smart speakers23
Combining replay and LoRA for continual learning in natural language understanding21
A transformer-based spelling error correction framework for Bangla and resource scarce Indic languages21
Improving self-supervised learning model for audio spoofing detection with layer-conditioned embedding fusion21
Accentron: Foreign accent conversion to arbitrary non-native speakers using zero-shot learning21
Preserving the beamforming effect for spatial cue-based pseudo-binaural dereverberation of a single source19
The use of Active Learning systems for stimulus selection and response modelling in perception experiments18
Symbolic and Statistical Learning Approaches to Speech Summarization: A Scoping Review18
A lightweight approach based on prompt for few-shot relation extraction18
Loanword identification based on web resources: A case study on wikipedia18
A mobile application using automatic speech analysis for classifying Alzheimer's disease and mild cognitive impairment17
Representation learning strategies to model pathological speech: Effect of multiple spectral resolutions16
Enhancing Arabic aspect-based sentiment analysis using deep learning models16
Unsupervised induction of inflectional families15
Conversations in the wild: Data collection, automatic generation and evaluation15
Editorial Board15
English–Assamese neural machine translation using prior alignment and pre-trained language model15
Dialect Identification using Chroma-Spectral Shape Features with Ensemble Technique14
Effects of cross-cultural language differences on social cognition during human-agent interaction in cooperative game environments14
A novel channel estimate for noise robust speech recognition14
Meta adversarial learning improves low-resource speech recognition13
Evidence and Axial Attention Guided Document-level Relation Extraction13
Editorial Board13
Adjustable deterministic pseudonymization of speech13
MPSA-DenseNet: A novel deep learning model for English accent classification12
Editorial Board12
Editorial Board12
Zero-Shot Strike: Testing the generalisation capabilities of out-of-the-box LLM models for depression detection12
SecNLP: An NLP classification model watermarking framework based on multi-task learning12
A multi-label emoji classification method using balanced pointwise mutual information-based feature selection12
A bias evaluation solution for multiple sensitive attribute speech recognition12
Addressing subjectivity in paralinguistic data labeling for improved classification performance: A case study with Spanish-speaking Mexican children using data balancing and semi-supervised learning11
A flexible BERT model enabling width- and depth-dynamic inference11
Improved relation extraction through key phrase identification using community detection on dependency trees11
Named entity recognition using neural language model and CRF for Hindi language11
FinD: Fine-grained discrepancy-based fake news detection enhanced by event abstract generation10
Effective infant cry signal analysis and reasoning using IARO based leaky Bi-LSTM model10
Neural multi-task learning for end-to-end Arabic aspect-based sentiment analysis10
Towards a unified assessment framework of speech pseudonymisation10
Offensive language detection in Tamil YouTube comments by adapters and cross-domain knowledge transfer10
A computational analysis of transcribed speech of people living with dementia: The Anchise 2022 Corpus10
Phase sensitive masking-based single channel speech enhancement using conditional generative adversarial network10
Towards inclusive automatic speech recognition10
Detection of vowel transition regions from Hindi language9
Conversation Initiation of Mothers, Fathers, and Toddlers in their Natural Home Environment9
A tag-based methodology for the detection of user repair strategies in task-oriented conversational agents9
A review of speaker diarization: Recent advances with deep learning9
Editorial Board9
Improving BERT with local context comprehension for multi-turn response selection in retrieval-based dialogue systems9
Prototypical networks relation classification model based on entity convolution9
Towards detecting the level of trust in the skills of a virtual assistant from the user’s speech9
Enhancing accuracy and privacy in speech-based depression detection through speaker disentanglement9
GenCeption: Evaluate vision LLMs with unlabeled unimodal data9
Generating identities with mixture models for speaker anonymization9
Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge9
Empirical Mode Decomposition articulation feature extraction on Parkinson’s Diadochokinesia8
Automatic speaker independent dysarthric speech intelligibility assessment system8
Automated grapheme-to-phoneme conversion for Central Kurdish based on optimality theory8
Hate speech and offensive language detection in Dravidian languages using deep ensemble framework8
Refining the evaluation of speech synthesis: A summary of the Blizzard Challenge 20238
Adaptive feature extraction for entity relation extraction8
End-to-End Speech-to-Text Translation: A Survey8
A neural network approach for speech enhancement and noise-robust bandwidth extension8
Towards lifelong human assisted speaker diarization8
Evaluating voice-assistant commands for dementia detection8
Test-retest reliability of acoustic and linguistic measures of speech tasks8
Generative adversarial networks for speech processing: A review8
Arabic speech recognition by end-to-end, modular systems and human8
Multiple time-instances features based approach for reference-free speech quality measurement8
A closer look at reinforcement learning-based automatic speech recognition8
Investigations on speech recognition systems for low-resource dialectal Arabic–English code-switching speech8
Unsupervised speech representation learning for behavior modeling using triplet enhanced contextualized networks7
Two in One: A multi-task framework for politeness turn identification and phrase extraction in goal-oriented conversations7
Measuring and implementing lexical alignment: A systematic literature review7
GTSO: Gradient tangent search optimization enabled voice transformer with speech intelligibility for aphasia7
Multilingual non-intrusive binaural intelligibility prediction based on phone classification7
An automated quality evaluation framework of psychotherapy conversations with local quality estimates7
Speech self-supervised representations benchmarking: A case for larger probing heads7
Significance of chirp MFCC as a feature in speech and audio applications7
Improving named entity correctness of abstractive summarization by generative negative sampling7
Three-stage modular speaker diarization collaborating with front-end techniques in the CHiME-8 NOTSOFAR-1 challenge7
A physical exertion inspired multi-task learning framework for detecting out-of-breath speech7
Morse wavelet transform-based features for voice liveness detection7
Classification of stuttering – The ComParE challenge and beyond7
Goal-oriented conditional variational autoencoders for proactive and knowledge-aware conversational recommender system7
Channel and channel subband selection for speaker diarization7
A potential relation trigger method for entity-relation quintuple extraction in text with excessive entities6
Accurate speaker counting, diarization and separation for advanced recognition of multichannel multispeaker conversations6
Automatic screening of mild cognitive impairment and Alzheimer’s disease by means of posterior-thresholding hesitation representation6
Analysis and classification of speech sounds of children with autism spectrum disorder using acoustic features6
A cross-attention augmented model for event-triggered context-aware story generation6
Building a text retrieval system for the Sanskrit language: Exploring indexing, stemming, and searching issues6
Assessing language models’ task and language transfer capabilities for sentiment analysis in dialog data6
Talking-heads attention-based knowledge representation for link prediction6
A knowledge-augmented heterogeneous graph convolutional network for aspect-level multimodal sentiment analysis6
SEBGM: Sentence Embedding Based on Generation Model with multi-task learning6
A new speech corpus of super-elderly Japanese for acoustic modeling6
C-KGE: Curriculum learning-based Knowledge Graph Embedding6
Optimizing pipeline task-oriented dialogue systems using post-processing networks6
Discovering phonetic inventories with crosslingual automatic speech recognition6
Spoofing countermeasure for fake speech detection using brute force features6
Lightweight and irreversible speech pseudonymization based on data-driven optimization of cascaded voice modification modules6
UniKDD: A Unified Generative model for Knowledge-driven Dialogue5
FE-CFNER: Feature Enhancement-based approach for Chinese Few-shot Named Entity Recognition5
Cross-lingual multi-speaker speech synthesis with limited bilingual training data5
Uncertainty-aware non-autoregressive neural machine translation5
Rep-MCA-former: An efficient multi-scale convolution attention encoder for text-independent speaker verification5
Direct enhancement of pre-trained speech embeddings for speech processing in noisy conditions5
Two evaluations on Ontology-style relation annotations5
Editorial Board5
Scale-aware dual-branch complex convolutional recurrent network for monaural speech enhancement5
Language-independent extractive automatic text summarization based on automatic keyword extraction5
Towards better Chinese-centric neural machine translation for low-resource languages5
A study of vowel nasalization using instantaneous spectra5
Exploring intrinsic information content models for addressing the issues of traditional semantic measures to evaluate verb similarity5
A novel word sense disambiguation approach using WordNet knowledge graph5
An optimal approach for text feature selection5
Predicting children’s perceived reading proficiency with prosody modeling4
Sequential routing framework: Fully capsule network-based speech recognition4
On significance of constant-Q transform for pop noise detection4
Editorial Board4
Copiously Quote Classics: Improving Chinese Poetry Generation with historical allusion knowledge4
TadaStride: Using time adaptive strides in audio data for effective downsampling4
An analysis of machine learning models for sentiment analysis of Tamil code-mixed data4
Spectral–temporal saliency masks and modulation tensorgrams for generalizable COVID-19 detection4
Speaking to remember: Model-based adaptive vocabulary learning using automatic speech recognition4
Neural referential form selection: Generalisability and interpretability4
A code-mixed task-oriented dialog dataset for medical domain4
Speaker anonymization by modifying fundamental frequency and x-vector singular value4
COMPASS: A creative support system that alerts novelists to the unnoticed missing contents4
Cross-lingual transfer learning for relation extraction using Universal Dependencies4
How to make embeddings suitable for PLDA4
LRetUNet: A U-Net-based retentive network for single-channel speech enhancement4
EMGVox-GAN: A transformative approach to EMG-based speech synthesis, enhancing clarity, and efficiency via extensive dataset utilization4
A semi-supervised high-quality pseudo labels algorithm based on multi-constraint optimization for speech deception detection4
Joint speaker diarization and speech recognition based on region proposal networks3
Editorial Board3
Multi-level context features extraction for named entity recognition3
Demystifying large language models in second language development research3
Knowledge-enhanced meta-prompt for few-shot relation extraction3
Analysis of Instantaneous Frequency Components of Speech Signals for Epoch Extraction3
Multi-task learning neural framework for categorizing sexism3
M-Sim: Multi-level Semantic Inference Model for Chinese short answer scoring in low-resource scenarios3
Knowledge-grounded dialogue modelling with dialogue-state tracking, domain tracking, and entity extraction3
Spoken language interaction with robots: Recommendations for future research3
LeBenchmark 2.0: A standardized, replicable and enhanced framework for self-supervised representations of French speech3
Single-channel speech enhancement using colored spectrograms3
Supervised speech separation combined with adaptive beamforming3
Editorial Board3
Train from scratch: Single-stage joint training of speech separation and recognition3
Deep learning based multi-source localization with source splitting and its effectiveness in multi-talker speech recognition3
New research on monaural speech segregation based on quality assessment3
Editorial Board3
Dereverberation of autoregressive envelopes for far-field speech recognition3
What’s so complex about conversational speech? A comparison of HMM-based and transformer-based ASR architectures3
Deep learning-based speaker-adaptive postfiltering with limited adaptation data for embedded text-to-speech synthesis systems3
An automatic Alzheimer’s disease classifier based on spontaneous spoken English3
Overlapped Speech Detection and speaker counting using distant microphone arrays3
Enhancing Turkish Coreference Resolution: Insights from deep learning, dropped pronouns, and multilingual transfer learning3
Joint emotion label space modeling for affect lexica3
Combining context-relevant features with multi-stage attention network for short text classification3
Editorial Board3
Modelling child comprehension: A case of suffixal passive construction in Korean3
Character expression for spoken dialogue systems with semi-supervised learning using Variational Auto-Encoder3
An experimental review of speaker diarization methods with application to two-speaker conversational telephone speech recordings3
Self-feeding training method for semi-supervised grammatical error correction3
Discriminating speech traits of Alzheimer's disease assessed through a corpus of reading task for Spanish language3
0.12780094146729