{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"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":"2101.09624","title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","created":"2021-01-24","cited_by_count":124},{"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":"2104.04045","title":"End-to-end speaker segmentation for overlap-aware resegmentation","created":"2021-04-08","cited_by_count":80},{"id":"1909.06247","title":"End-to-End Neural Speaker Diarization with Self-attention","created":"2019-09-13","cited_by_count":77},{"id":"2002.08933","title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","created":"2020-02-20","cited_by_count":75},{"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":"1712.08273","title":"Recurrent Pixel Embedding for Instance Grouping","created":"2017-12-22","cited_by_count":58},{"id":"2012.01477","title":"The Third DIHARD Diarization Challenge","created":"2020-12-02","cited_by_count":49},{"id":"1810.04719","title":"Fully Supervised Speaker Diarization","created":"2018-10-10","cited_by_count":47},{"id":"2104.01466","title":"ECAPA-TDNN Embeddings for Speaker Diarization","created":"2021-04-03","cited_by_count":47},{"id":"1906.07839","title":"The Second DIHARD Diarization Challenge: Dataset, task, and baselines","created":"2019-06-18","cited_by_count":39},{"id":"1703.10277","title":"Semantic Instance Segmentation via Deep Metric Learning","created":"2017-03-30","cited_by_count":37},{"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":"2009.04323","title":"VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition","created":"2020-09-09","cited_by_count":32},{"id":"2109.11641","title":"Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detection","created":"2021-09-23","cited_by_count":32},{"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":"1611.08930","title":"Deep attractor network for single-microphone speaker separation","created":"2016-11-27","cited_by_count":26},{"id":"1908.04284","title":"Personal VAD: Speaker-Conditioned Voice Activity Detection","created":"2019-08-12","cited_by_count":25},{"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":"2106.10654","title":"Encoder-Decoder Based Attractors for End-to-End Neural Diarization","created":"2021-06-20","cited_by_count":20},{"id":"2010.11458","title":"Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020","created":"2020-10-22","cited_by_count":18},{"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":"2108.03342","title":"Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker","created":"2021-08-07","cited_by_count":15},{"id":"2109.06483","title":"Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation","created":"2021-09-14","cited_by_count":15},{"id":"1904.03065","title":"Recursive speech separation for unknown number of speakers","created":"2019-04-05","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":"2012.10055","title":"End-to-End Speaker Diarization as Post-Processing","created":"2020-12-18","cited_by_count":13},{"id":"2106.07167","title":"End-to-end Neural Diarization: From Transformer to Conformer","created":"2021-06-14","cited_by_count":12},{"id":"2002.11356","title":"BUT System for the Second DIHARD Speech Diarization Challenge","created":"2020-02-26","cited_by_count":11},{"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":"2203.15974","title":"Multi-scale Speaker Diarization with Dynamic Scale Weighting","created":"2022-03-30","cited_by_count":11},{"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":"2102.01363","title":"The Hitachi-JHU DIHARD III System: Competitive End-to-End Neural Diarization and X-Vector Clustering Systems Combined by DOVER-Lap","created":"2021-02-02","cited_by_count":8},{"id":"2104.02878","title":"Three-class Overlapped Speech Detection using a Convolutional Recurrent Neural Network","created":"2021-04-07","cited_by_count":8},{"id":"2105.02096","title":"End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings","created":"2021-05-05","cited_by_count":7},{"id":"1812.07205","title":"Audiovisual speaker diarization of TV series","created":"2018-12-18","cited_by_count":5},{"id":"2006.14150","title":"Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals","created":"2020-06-25","cited_by_count":5},{"id":"2105.13802","title":"DIVE: End-to-end Speech Diarization via Iterative Speaker Embedding","created":"2021-05-28","cited_by_count":5},{"id":"2106.04078","title":"End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection","created":"2021-06-08","cited_by_count":5},{"id":"2109.06824","title":"Self-Supervised Metric Learning With Graph Clustering For Speaker Diarization","created":"2021-09-14","cited_by_count":4},{"id":"1911.01266","title":"Supervised online diarization with sample mean loss for multi-domain data","created":"2019-11-04","cited_by_count":3},{"id":"2106.04764","title":"Semi-Supervised Training with Pseudo-Labeling for End-to-End Neural Diarization","created":"2021-06-09","cited_by_count":3},{"id":"2111.13803","title":"Low-Latency Online Speaker Diarization with Graph-Based Label Generation","created":"2021-11-27","cited_by_count":3},{"id":"2202.06524","title":"Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture model","created":"2022-02-14","cited_by_count":3}],"next_cursor":null}