{"list":"other","total":56,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601},{"id":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"2006.13979","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","created":"2020-06-24","cited_by_count":501},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260},{"id":"1609.06773","title":"Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning","created":"2016-09-21","cited_by_count":257},{"id":"2104.03502","title":"Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings","created":"2021-04-08","cited_by_count":162},{"id":"2004.06833","title":"Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge","created":"2020-04-14","cited_by_count":104},{"id":"1907.13511","title":"Personalizing ASR for Dysarthric and Accented Speech with Limited Data","created":"2019-07-31","cited_by_count":45},{"id":"1601.02828","title":"Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation","created":"2016-01-12","cited_by_count":40},{"id":"2109.15053","title":"Fine-tuning wav2vec2 for speaker recognition","created":"2021-09-30","cited_by_count":39},{"id":"2106.15684","title":"Alzheimer's Dementia Recognition Using Acoustic, Lexical, Disfluency and Speech Pause Features Robust to Noisy Inputs","created":"2021-06-29","cited_by_count":27},{"id":"2201.05562","title":"Investigation of Data Augmentation Techniques for Disordered Speech Recognition","created":"2022-01-14","cited_by_count":27},{"id":"2110.06280","title":"S3PRL-VC: Open-source Voice Conversion Framework with Self-supervised Speech Representations","created":"2021-10-12","cited_by_count":23},{"id":"2204.00770","title":"Speaker adaptation for Wav2vec2 based dysarthric ASR","created":"2022-04-02","cited_by_count":21},{"id":"2202.10290","title":"Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition","created":"2022-02-21","cited_by_count":19},{"id":"2108.00899","title":"Adversarial Data Augmentation for Disordered Speech Recognition","created":"2021-08-02","cited_by_count":18},{"id":"2011.01686","title":"Improved End-to-End Dysarthric Speech Recognition via Meta-learning Based Model Re-initialization","created":"2020-11-03","cited_by_count":17},{"id":"2201.05845","title":"Recent Progress in the CUHK Dysarthric Speech Recognition System","created":"2022-01-15","cited_by_count":17},{"id":"2204.01670","title":"Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognition","created":"2022-04-04","cited_by_count":17},{"id":"1907.00835","title":"UltraSuite: A Repository of Ultrasound and Acoustic Data from Child Speech Therapy Sessions","created":"2019-07-01","cited_by_count":16},{"id":"2205.06445","title":"Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition","created":"2022-05-13","cited_by_count":16},{"id":"2203.15431","title":"Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition","created":"2022-03-29","cited_by_count":15},{"id":"1804.10325","title":"Simulating dysarthric speech for training data augmentation in clinical speech applications","created":"2018-04-27","cited_by_count":14},{"id":"2110.04612","title":"Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasets","created":"2021-10-09","cited_by_count":14},{"id":"2203.15796","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition","created":"2022-03-29","cited_by_count":14},{"id":"2302.14564","title":"Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition","created":"2023-02-28","cited_by_count":14},{"id":"2011.09804","title":"TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos","created":"2020-11-19","cited_by_count":12},{"id":"2206.13232","title":"Conformer Based Elderly Speech Recognition System for Alzheimer's Disease Detection","created":"2022-06-23","cited_by_count":12},{"id":"2110.08213","title":"Towards Identity Preserving Normal to Dysarthric Voice Conversion","created":"2021-10-15","cited_by_count":10},{"id":"2201.11571","title":"Synthesizing Dysarthric Speech Using Multi-talker TTS for Dysarthric Speech Recognition","created":"2022-01-27","cited_by_count":10},{"id":"2201.09422","title":"Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition","created":"2022-01-24","cited_by_count":9},{"id":"2203.10274","title":"Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition","created":"2022-03-19","cited_by_count":9},{"id":"2206.13758","title":"Exploring linguistic feature and model combination for speech recognition based automatic AD detection","created":"2022-06-28","cited_by_count":9},{"id":"2201.04908","title":"The Effectiveness of Time Stretching for Enhancing Dysarthric Speech for Improved Dysarthric Speech Recognition","created":"2022-01-13","cited_by_count":8},{"id":"2305.10659","title":"Use of Speech Impairment Severity for Dysarthric Speech Recognition","created":"2023-05-18","cited_by_count":8},{"id":"1907.01413","title":"Speaker-independent classification of phonetic segments from raw ultrasound in child speech","created":"2019-07-01","cited_by_count":7},{"id":"2206.07327","title":"Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition","created":"2022-06-15","cited_by_count":7},{"id":"2211.01646","title":"Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition","created":"2022-11-03","cited_by_count":7},{"id":"2106.01415","title":"A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion","created":"2021-06-02","cited_by_count":6},{"id":"2210.16539","title":"Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection","created":"2022-10-29","cited_by_count":6},{"id":"2211.00089","title":"An analysis of degenerating speech due to progressive dysarthria on ASR performance","created":"2022-10-31","cited_by_count":6},{"id":"2303.03049","title":"Cross-Lingual Transfer Learning for Alzheimer's Detection From Spontaneous Speech","created":"2023-03-06","cited_by_count":6},{"id":"2306.10588","title":"DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model","created":"2023-06-18","cited_by_count":6},{"id":"2111.11859","title":"Longitudinal Speech Biomarkers for Automated Alzheimer's Detection","created":"2021-11-22","cited_by_count":5},{"id":"2203.14593","title":"On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition","created":"2022-03-28","cited_by_count":5},{"id":"1905.06533","title":"Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech","created":"2019-05-16","cited_by_count":4},{"id":"2106.08313","title":"A Study into Pre-training Strategies for Spoken Language Understanding on Dysarthric Speech","created":"2021-06-15","cited_by_count":4},{"id":"2206.11596","title":"Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems","created":"2022-06-23","cited_by_count":4},{"id":"2306.15265","title":"Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition","created":"2023-06-27","cited_by_count":4}],"next_cursor":null}