{"list":"other","total":69,"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"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":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"2005.07143","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","created":"2020-05-14","cited_by_count":628},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2101.00390","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","created":"2021-01-02","cited_by_count":463},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"id":"2106.06909","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","created":"2021-06-13","cited_by_count":399},{"id":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"2002.02562","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","created":"2020-02-07","cited_by_count":235},{"id":"1910.12638","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","created":"2019-10-25","cited_by_count":198},{"id":"2007.06028","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","created":"2020-07-12","cited_by_count":188},{"id":"1904.03240","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","created":"2019-04-05","cited_by_count":186},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169},{"id":"2104.01027","title":"Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training","created":"2021-04-02","cited_by_count":151},{"id":"2001.09239","title":"Multi-task self-supervised learning for Robust Speech Recognition","created":"2020-01-25","cited_by_count":130},{"id":"2101.09624","title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","created":"2021-01-24","cited_by_count":124},{"id":"1911.08460","title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","created":"2019-11-19","cited_by_count":120},{"id":"2002.02848","title":"Unsupervised pretraining transfers well across languages","created":"2020-02-07","cited_by_count":101},{"id":"2005.03191","title":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","created":"2020-05-07","cited_by_count":97},{"id":"1709.07902","title":"Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data","created":"2017-09-22","cited_by_count":93},{"id":"1901.08810","title":"Unsupervised speech representation learning using WaveNet autoencoders","created":"2019-01-25","cited_by_count":90},{"id":"1909.05952","title":"End-to-End Neural Speaker Diarization with Permutation-Free Objectives","created":"2019-09-12","cited_by_count":88},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88},{"id":"1904.03416","title":"Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks","created":"2019-04-06","cited_by_count":87},{"id":"2104.02133","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","created":"2021-04-05","cited_by_count":83},{"id":"1910.12607","title":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","created":"2019-10-23","cited_by_count":82},{"id":"1910.11455","title":"Recognizing long-form speech using streaming end-to-end models","created":"2019-10-24","cited_by_count":77},{"id":"2012.06659","title":"DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization","created":"2020-12-11","cited_by_count":77},{"id":"2101.07597","title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","created":"2021-01-19","cited_by_count":77},{"id":"2001.11482","title":"Continuous speech separation: dataset and analysis","created":"2020-01-30","cited_by_count":74},{"id":"2010.11745","title":"Rethinking Evaluation in ASR: Are Our Models Robust Enough?","created":"2020-10-22","cited_by_count":73},{"id":"2012.14952","title":"Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks","created":"2020-12-29","cited_by_count":73},{"id":"2106.16138","title":"XLM-E: Cross-lingual Language Model Pre-training via ELECTRA","created":"2021-06-30","cited_by_count":72},{"id":"2005.09921","title":"End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors","created":"2020-05-20","cited_by_count":71},{"id":"2005.08392","title":"Vector-Quantized Autoregressive Predictive Coding","created":"2020-05-17","cited_by_count":69},{"id":"2109.06870","title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","created":"2021-09-14","cited_by_count":68},{"id":"1912.01679","title":"Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition","created":"2019-12-03","cited_by_count":66},{"id":"2011.00406","title":"Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies","created":"2020-11-01","cited_by_count":47},{"id":"2101.01902","title":"Interspeech 2021 Deep Noise Suppression Challenge","created":"2021-01-06","cited_by_count":47},{"id":"2110.05752","title":"UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training","created":"2021-10-12","cited_by_count":45},{"id":"1812.07625","title":"wav2letter++: The Fastest Open-source Speech Recognition System","created":"2018-12-18","cited_by_count":42},{"id":"2008.05773","title":"Continuous Speech Separation with Conformer","created":"2020-08-13","cited_by_count":36},{"id":"1808.05312","title":"Toward domain-invariant speech recognition via large scale training","created":"2018-08-16","cited_by_count":35},{"id":"1704.04222","title":"Learning Latent Representations for Speech Generation and Transformation","created":"2017-04-13","cited_by_count":27},{"id":"2004.05274","title":"Improved Speech Representations with Multi-Target Autoregressive Predictive Coding","created":"2020-04-11","cited_by_count":23},{"id":"2010.11255","title":"The IDLAB VoxSRC-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification","created":"2020-10-21","cited_by_count":23},{"id":"2105.09040","title":"Advances in integration of end-to-end neural and clustering-based diarization for real conversational speech","created":"2021-05-19","cited_by_count":23},{"id":"2109.01989","title":"The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021","created":"2021-09-05","cited_by_count":20},{"id":"1912.03010","title":"Semantic Mask for Transformer based End-to-End Speech Recognition","created":"2019-12-06","cited_by_count":18},{"id":"2010.12180","title":"Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer","created":"2020-10-23","cited_by_count":16},{"id":"2107.01545","title":"Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors","created":"2021-07-04","cited_by_count":15},{"id":"2006.01796","title":"Neural Speaker Diarization with Speaker-Wise Chain Rule","created":"2020-06-02","cited_by_count":14},{"id":"2107.01922","title":"Investigation of Practical Aspects of Single Channel Speech Separation for ASR","created":"2021-07-05","cited_by_count":8},{"id":"2110.04891","title":"Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition","created":"2021-10-10","cited_by_count":7}],"next_cursor":null}