{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"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":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"2206.11253","title":"Towards Robust Blind Face Restoration with Codebook Lookup Transformer","created":"2022-06-22","cited_by_count":231},{"id":"2007.06028","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","created":"2020-07-12","cited_by_count":188},{"id":"2006.12847","title":"Real Time Speech Enhancement in the Waveform Domain","created":"2020-06-23","cited_by_count":186},{"id":"2202.01855","title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition","created":"2022-02-03","cited_by_count":162},{"id":"2202.05256","title":"Conditional Diffusion Probabilistic Model for Speech Enhancement","created":"2022-02-10","cited_by_count":132},{"id":"1711.00541","title":"TasNet: time-domain audio separation network for real-time, single-channel speech separation","created":"2017-11-01","cited_by_count":115},{"id":"2005.14327","title":"On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition","created":"2020-05-28","cited_by_count":63},{"id":"1911.04697","title":"PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network","created":"2019-11-12","cited_by_count":51},{"id":"2104.13002","title":"DPT-FSNet: Dual-path Transformer Based Full-band and Sub-band Fusion Network for Speech Enhancement","created":"2021-04-27","cited_by_count":33},{"id":"1910.09932","title":"Improving Transformer-based Speech Recognition Using Unsupervised Pre-training","created":"2019-10-22","cited_by_count":30},{"id":"2203.15321","title":"Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data","created":"2022-03-29","cited_by_count":30},{"id":"2201.06685","title":"How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR","created":"2022-01-18","cited_by_count":28},{"id":"2005.09684","title":"Exploring Transformers for Large-Scale Speech Recognition","created":"2020-05-19","cited_by_count":24},{"id":"2201.08930","title":"A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognition","created":"2022-01-22","cited_by_count":22},{"id":"2210.15324","title":"Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning","created":"2022-10-27","cited_by_count":22},{"id":"2212.05301","title":"Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning","created":"2022-12-10","cited_by_count":22},{"id":"1903.04567","title":"Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling","created":"2019-03-11","cited_by_count":21},{"id":"2110.05267","title":"Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition","created":"2021-10-11","cited_by_count":18},{"id":"2204.00540","title":"End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation","created":"2022-04-01","cited_by_count":17},{"id":"2009.01941","title":"Dense CNN with Self-Attention for Time-Domain Speech Enhancement","created":"2020-09-03","cited_by_count":16},{"id":"2110.04934","title":"Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition","created":"2021-10-11","cited_by_count":16},{"id":"2110.15430","title":"Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction","created":"2021-10-28","cited_by_count":13},{"id":"2107.10701","title":"Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech","created":"2021-07-22","cited_by_count":11},{"id":"2112.09382","title":"Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem","created":"2021-12-17","cited_by_count":11},{"id":"2302.11989","title":"Metric-oriented Speech Enhancement using Diffusion Probabilistic Model","created":"2023-02-23","cited_by_count":11},{"id":"2203.14838","title":"Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition","created":"2022-03-28","cited_by_count":10},{"id":"2302.11131","title":"Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation","created":"2023-02-22","cited_by_count":10},{"id":"2302.11362","title":"Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition","created":"2023-02-22","cited_by_count":10},{"id":"1903.00739","title":"Speech Recognition with no speech or with noisy speech","created":"2019-03-02","cited_by_count":9},{"id":"2102.06237","title":"An Investigation of End-to-End Models for Robust Speech Recognition","created":"2021-02-11","cited_by_count":9},{"id":"2205.13293","title":"Joint Training of Speech Enhancement and Self-supervised Model for Noise-robust ASR","created":"2022-05-26","cited_by_count":9},{"id":"2302.11981","title":"Unsupervised Noise adaptation using Data Simulation","created":"2023-02-23","cited_by_count":9},{"id":"2011.04249","title":"Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition","created":"2020-11-09","cited_by_count":8},{"id":"2207.03067","title":"Cross-Scale Vector Quantization for Scalable Neural Speech Coding","created":"2022-07-07","cited_by_count":3}],"next_cursor":null}