{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1511.06335","title":"Unsupervised Deep Embedding for Clustering Analysis","created":"2015-11-19","cited_by_count":767},{"id":"1809.07454","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","created":"2018-09-20","cited_by_count":406},{"id":"1708.07524","title":"Supervised Speech Separation Based on Deep Learning: An Overview","created":"2017-08-24","cited_by_count":216},{"id":"1508.04306","title":"Deep clustering: Discriminative embeddings for segmentation and separation","created":"2015-08-18","cited_by_count":212},{"id":"2004.09249","title":"CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings","created":"2020-04-20","cited_by_count":132},{"id":"1703.06284","title":"Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks","created":"2017-03-18","cited_by_count":98},{"id":"1803.10609","title":"The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines","created":"2018-03-28","cited_by_count":92},{"id":"1909.05952","title":"End-to-End Neural Speaker Diarization with Permutation-Free Objectives","created":"2019-09-12","cited_by_count":88},{"id":"2003.12687","title":"Serialized Output Training for End-to-End Overlapped Speech Recognition","created":"2020-03-28","cited_by_count":87},{"id":"2007.01216","title":"Spot the conversation: speaker diarisation in the wild","created":"2020-07-02","cited_by_count":79},{"id":"1909.06247","title":"End-to-End Neural Speaker Diarization with Self-attention","created":"2019-09-13","cited_by_count":77},{"id":"2001.11482","title":"Continuous speech separation: dataset and analysis","created":"2020-01-30","cited_by_count":74},{"id":"1710.10468","title":"Speaker Diarization with LSTM","created":"2017-10-28","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":"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":"2005.07272","title":"Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenario","created":"2020-05-14","cited_by_count":68},{"id":"1806.01822","title":"Relational recurrent neural networks","created":"2018-06-05","cited_by_count":65},{"id":"1610.05256","title":"Achieving Human Parity in Conversational Speech Recognition","created":"2016-10-17","cited_by_count":63},{"id":"1611.00822","title":"Learning Deep Embeddings with Histogram Loss","created":"2016-11-02","cited_by_count":52},{"id":"1907.05337","title":"Joint Speech Recognition and Speaker Diarization via Sequence Transduction","created":"2019-07-09","cited_by_count":49},{"id":"1810.04719","title":"Fully Supervised Speaker Diarization","created":"2018-10-10","cited_by_count":47},{"id":"2006.10930","title":"Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers","created":"2020-06-19","cited_by_count":41},{"id":"1703.02136","title":"English Conversational Telephone Speech Recognition by Humans and Machines","created":"2017-03-06","cited_by_count":40},{"id":"1906.07839","title":"The Second DIHARD Diarization Challenge: Dataset, task, and baselines","created":"2019-06-18","cited_by_count":39},{"id":"2003.02405","title":"Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap","created":"2020-03-05","cited_by_count":36},{"id":"2010.13366","title":"Integrating end-to-end neural and clustering-based diarization: Getting the best of both worlds","created":"2020-10-26","cited_by_count":35},{"id":"2011.02014","title":"Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis","created":"2020-11-03","cited_by_count":35},{"id":"1704.01985","title":"Recognizing Multi-talker Speech with Permutation Invariant Training","created":"2017-03-22","cited_by_count":33},{"id":"1805.05826","title":"A Purely End-to-end System for Multi-speaker Speech Recognition","created":"2018-05-15","cited_by_count":30},{"id":"2008.04546","title":"Investigation of End-To-End Speaker-Attributed ASR for Continuous Multi-Talker Recordings","created":"2020-08-11","cited_by_count":28},{"id":"1910.11646","title":"Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detection","created":"2019-10-25","cited_by_count":27},{"id":"2012.06867","title":"VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge","created":"2020-12-12","cited_by_count":27},{"id":"1811.02062","title":"End-to-End Monaural Multi-speaker ASR System without Pretraining","created":"2018-11-05","cited_by_count":26},{"id":"1810.03655","title":"Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks","created":"2018-10-08","cited_by_count":23},{"id":"1912.04979","title":"Advances in Online Audio-Visual Meeting Transcription","created":"2019-12-10","cited_by_count":23},{"id":"2005.08072","title":"Speech Recognition and Multi-Speaker Diarization of Long Conversations","created":"2020-05-16","cited_by_count":23},{"id":"2011.01997","title":"DOVER-Lap: A Method for Combining Overlap-aware Diarization Outputs","created":"2020-11-03","cited_by_count":19},{"id":"1711.07274","title":"Speech recognition for medical conversations","created":"2017-11-20","cited_by_count":18},{"id":"2010.11458","title":"Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020","created":"2020-10-22","cited_by_count":18},{"id":"1907.10393","title":"LSTM based Similarity Measurement with Spectral Clustering for Speaker Diarization","created":"2019-07-23","cited_by_count":17},{"id":"1906.10876","title":"Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition","created":"2019-06-26","cited_by_count":16},{"id":"2002.06220","title":"Speaker Diarization with Region Proposal Network","created":"2020-02-14","cited_by_count":16},{"id":"1912.02522","title":"VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge","created":"2019-12-05","cited_by_count":14},{"id":"2004.06756","title":"Speaker Diarization with Lexical Information","created":"2020-04-13","cited_by_count":14},{"id":"2006.01796","title":"Neural Speaker Diarization with Speaker-Wise Chain Rule","created":"2020-06-02","cited_by_count":14},{"id":"2006.02616","title":"Online End-to-End Neural Diarization with Speaker-Tracing Buffer","created":"2020-06-04","cited_by_count":14},{"id":"1909.08103","title":"Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models","created":"2019-09-17","cited_by_count":13},{"id":"2012.10055","title":"End-to-End Speaker Diarization as Post-Processing","created":"2020-12-18","cited_by_count":13},{"id":"1805.10731","title":"Multimodal Speaker Segmentation and Diarization using Lexical and Acoustic Cues via Sequence to Sequence Neural Networks","created":"2018-05-28","cited_by_count":12},{"id":"2011.02678","title":"BW-EDA-EEND: Streaming End-to-End Neural Speaker Diarization for a Variable Number of Speakers","created":"2020-11-05","cited_by_count":11},{"id":"2011.02921","title":"Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR","created":"2020-11-03","cited_by_count":11},{"id":"1905.12230","title":"Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR","created":"2019-05-29","cited_by_count":10},{"id":"2003.03987","title":"Tackling real noisy reverberant meetings with all-neural source separation, counting, and diarization system","created":"2020-03-09","cited_by_count":10},{"id":"2011.10527","title":"Multi-Scale Speaker Diarization With Neural Affinity Score Fusion","created":"2020-11-20","cited_by_count":10},{"id":"2005.11371","title":"Speaker diarization with session-level speaker embedding refinement using graph neural networks","created":"2020-05-22","cited_by_count":9},{"id":"2006.05815","title":"Third DIHARD Challenge Evaluation Plan","created":"2020-06-04","cited_by_count":8},{"id":"1909.08090","title":"DOVER: A Method for Combining Diarization Outputs","created":"2019-09-17","cited_by_count":6},{"id":"1911.11927","title":"Automatic prediction of suicidal risk in military couples using multimodal interaction cues from couples conversations","created":"2019-11-27","cited_by_count":6},{"id":"2011.03110","title":"Exploring End-to-End Multi-channel ASR with Bias Information for Meeting Transcription","created":"2020-11-05","cited_by_count":6},{"id":"2012.09727","title":"Continuous Speech Separation Using Speaker Inventory for Long Multi-talker Recording","created":"2020-12-17","cited_by_count":5},{"id":"1811.02641","title":"Building Corpora for Single-Channel Speech Separation Across Multiple Domains","created":"2018-11-06","cited_by_count":4},{"id":"2006.07898","title":"The JHU Multi-Microphone Multi-Speaker ASR System for the CHiME-6 Challenge","created":"2020-06-14","cited_by_count":4},{"id":"1903.02844","title":"Voice Activity Detection: Merging Source and Filter-based Information","created":"2019-03-07","cited_by_count":3},{"id":"1909.00082","title":"Enhancements for Audio-only Diarization Systems","created":"2019-08-30","cited_by_count":2},{"id":"2001.05118","title":"A Memory Augmented Architecture for Continuous Speaker Identification in Meetings","created":"2020-01-15","cited_by_count":2}],"next_cursor":null}