{"list":"other","total":55,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"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":"1811.02508","title":"SDR - half-baked or well done?","created":"2018-11-06","cited_by_count":423},{"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":"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":"2005.11262","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","created":"2020-05-22","cited_by_count":155},{"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":"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":"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":"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":"2001.11482","title":"Continuous speech separation: dataset and analysis","created":"2020-01-30","cited_by_count":74},{"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":"2007.13975","title":"Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation","created":"2020-07-28","cited_by_count":68},{"id":"2110.04410","title":"TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context","created":"2021-10-08","cited_by_count":62},{"id":"2003.01531","title":"Voice Separation with an Unknown Number of Multiple Speakers","created":"2020-02-29","cited_by_count":46},{"id":"2005.04132","title":"Asteroid: the PyTorch-based audio source separation toolkit for researchers","created":"2020-05-08","cited_by_count":45},{"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":"1910.11646","title":"Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detection","created":"2019-10-25","cited_by_count":27},{"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":"2010.11458","title":"Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020","created":"2020-10-22","cited_by_count":18},{"id":"2002.06220","title":"Speaker Diarization with Region Proposal Network","created":"2020-02-14","cited_by_count":16},{"id":"2201.10800","title":"SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation","created":"2022-01-26","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":"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":"2006.02616","title":"Online End-to-End Neural Diarization with Speaker-Tracing Buffer","created":"2020-06-04","cited_by_count":14},{"id":"2003.02966","title":"End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification","created":"2020-02-24","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":"2010.11718","title":"Analysis of the BUT Diarization System for VoxConverse Challenge","created":"2020-10-22","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":"2206.07340","title":"On the Design and Training Strategies for RNN-based Online Neural Speech Separation Systems","created":"2022-06-15","cited_by_count":9},{"id":"1912.08462","title":"End-to-end training of time domain audio separation and recognition","created":"2019-12-18","cited_by_count":8},{"id":"2011.02900","title":"Multi-class Spectral Clustering with Overlaps for Speaker Diarization","created":"2020-11-05","cited_by_count":8},{"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":"2206.02432","title":"Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors","created":"2022-06-06","cited_by_count":8},{"id":"2110.10812","title":"REAL-M: Towards Speech Separation on Real Mixtures","created":"2021-10-20","cited_by_count":7},{"id":"2105.13802","title":"DIVE: End-to-end Speech Diarization via Iterative Speaker Embedding","created":"2021-05-28","cited_by_count":5},{"id":"2204.02306","title":"Low-Latency Speech Separation Guided Diarization for Telephone Conversations","created":"2022-04-05","cited_by_count":5},{"id":"1904.06478","title":"Low-Latency Speaker-Independent Continuous Speech Separation","created":"2019-04-13","cited_by_count":4},{"id":"2109.06824","title":"Self-Supervised Metric Learning With Graph Clustering For Speaker Diarization","created":"2021-09-14","cited_by_count":4},{"id":"2011.10345","title":"Deep Multi-Frame MVDR Filtering for Single-Microphone Speech Enhancement","created":"2020-11-20","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":"2204.07566","title":"Improving Frame-Online Neural Speech Enhancement with Overlapped-Frame Prediction","created":"2022-04-15","cited_by_count":1},{"id":"2205.15700","title":"Conversational Speech Separation: an Evaluation Study for Streaming Applications","created":"2022-05-31","cited_by_count":1}],"next_cursor":null}