{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"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":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"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":"2105.01051","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":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"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":"1809.07454","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","created":"2018-09-20","cited_by_count":406},{"id":"1709.05522","title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","created":"2017-09-16","cited_by_count":373},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"id":"1909.09577","title":"NeMo: a toolkit for building AI applications using Neural Modules","created":"2019-09-14","cited_by_count":235},{"id":"1805.04699","title":"TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation","created":"2018-05-12","cited_by_count":226},{"id":"1705.09792","title":"Deep Complex Networks","created":"2017-05-27","cited_by_count":217},{"id":"1508.04306","title":"Deep clustering: Discriminative embeddings for segmentation and separation","created":"2015-08-18","cited_by_count":212},{"id":"1909.06317","title":"A Comparative Study on Transformer vs RNN in Speech Applications","created":"2019-09-13","cited_by_count":211},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"1904.03670","title":"Speech Model Pre-training for End-to-End Spoken Language Understanding","created":"2019-04-07","cited_by_count":193},{"id":"2006.12847","title":"Real Time Speech Enhancement in the Waveform Domain","created":"2020-06-23","cited_by_count":186},{"id":"2010.13154","title":"Attention is All You Need in Speech Separation","created":"2020-10-25","cited_by_count":185},{"id":"2002.04688","title":"fastai: A Layered API for Deep Learning","created":"2020-02-11","cited_by_count":183},{"id":"1910.06379","title":"Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation","created":"2019-10-14","cited_by_count":182},{"id":"1911.01255","title":"pyannote.audio: neural building blocks for speaker diarization","created":"2019-11-04","cited_by_count":181},{"id":"1907.01160","title":"WHAM!: Extending Speech Separation to Noisy Environments","created":"2019-07-02","cited_by_count":156},{"id":"2005.11262","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","created":"2020-05-22","cited_by_count":155},{"id":"2005.13981","title":"The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results","created":"2020-05-16","cited_by_count":133},{"id":"2104.03538","title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","created":"2021-04-08","cited_by_count":114},{"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":"1910.10261","title":"QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions","created":"2019-10-22","cited_by_count":94},{"id":"1802.08395","title":"Towards end-to-end spoken language understanding","created":"2018-02-23","cited_by_count":92},{"id":"1902.08295","title":"Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling","created":"2019-02-21","cited_by_count":86},{"id":"1904.03288","title":"Jasper: An End-to-End Convolutional Neural Acoustic Model","created":"2019-04-05","cited_by_count":76},{"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":"1807.10857","title":"A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition","created":"2018-07-27","cited_by_count":66},{"id":"1809.09190","title":"From Audio to Semantics: Approaches to end-to-end spoken language understanding","created":"2018-09-24","cited_by_count":63},{"id":"1910.10279","title":"WHAMR!: Noisy and Reverberant Single-Channel Speech Separation","created":"2019-10-22","cited_by_count":61},{"id":"1910.12592","title":"BUT System Description to VoxCeleb Speaker Recognition Challenge 2019","created":"2019-10-16","cited_by_count":54},{"id":"1803.10225","title":"Light Gated Recurrent Units for Speech Recognition","created":"2018-03-26","cited_by_count":48},{"id":"2104.01466","title":"ECAPA-TDNN Embeddings for Speaker Diarization","created":"2021-04-03","cited_by_count":47},{"id":"2005.04132","title":"Asteroid: the PyTorch-based audio source separation toolkit for researchers","created":"2020-05-08","cited_by_count":45},{"id":"1806.04418","title":"Quaternion Recurrent Neural Networks","created":"2018-06-12","cited_by_count":41},{"id":"1811.07453","title":"The PyTorch-Kaldi Speech Recognition Toolkit","created":"2018-11-19","cited_by_count":40},{"id":"2104.01721","title":"Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition","created":"2021-04-05","cited_by_count":34},{"id":"1909.08723","title":"Espresso: A Fast End-to-end Neural Speech Recognition Toolkit","created":"2019-09-18","cited_by_count":31},{"id":"1805.05225","title":"RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition","created":"2018-05-14","cited_by_count":30},{"id":"2011.03706","title":"ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integration","created":"2020-11-07","cited_by_count":22},{"id":"2104.07253","title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","created":"2021-04-15","cited_by_count":22},{"id":"2010.03432","title":"WER we are and WER we think we are","created":"2020-10-07","cited_by_count":19},{"id":"2104.01604","title":"Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers","created":"2021-04-04","cited_by_count":11},{"id":"1803.09816","title":"Spectral feature mapping with mimic loss for robust speech recognition","created":"2018-03-26","cited_by_count":8},{"id":"1706.05765","title":"An Empirical Study of Mini-Batch Creation Strategies for Neural Machine Translation","created":"2017-06-19","cited_by_count":6},{"id":"1812.00115","title":"Lightweight and Optimized Sound Source Localization and Tracking Methods for Open and Closed Microphone Array Configurations","created":"2018-12-01","cited_by_count":6},{"id":"2007.09635","title":"Meta-learning with Latent Space Clustering in Generative Adversarial Network for Speaker Diarization","created":"2020-07-19","cited_by_count":3},{"id":"1703.08471","title":"Batch-normalized joint training for DNN-based distant speech recognition","created":"2017-03-24","cited_by_count":1},{"id":"2005.09587","title":"GEV Beamforming Supported by DOA-based Masks Generated on Pairs of Microphones","created":"2020-05-19","cited_by_count":1}],"next_cursor":null}