{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"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":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406},{"id":"1909.09577","title":"NeMo: a toolkit for building AI applications using Neural Modules","created":"2019-09-14","cited_by_count":235},{"id":"1508.04306","title":"Deep clustering: Discriminative embeddings for segmentation and separation","created":"2015-08-18","cited_by_count":212},{"id":"1607.00325","title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","created":"2016-07-01","cited_by_count":191},{"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":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129},{"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":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114},{"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":"2001.11482","title":"Continuous speech separation: dataset and analysis","created":"2020-01-30","cited_by_count":74},{"id":"2401.16658","title":"OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer","created":"2024-01-30","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":"2110.07393","title":"M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge","created":"2021-10-14","cited_by_count":71},{"id":"1911.02242","title":"A comparison of end-to-end models for long-form speech recognition","created":"2019-11-06","cited_by_count":42},{"id":"2002.03921","title":"End-to-End Multi-speaker Speech Recognition with Transformer","created":"2020-02-10","cited_by_count":42},{"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":"2308.12792","title":"Sparks of Large Audio Models: A Survey and Outlook","created":"2023-08-24","cited_by_count":41},{"id":"2104.02128","title":"End-to-End Speaker-Attributed ASR with Transformer","created":"2021-04-05","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":"2103.16776","title":"Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone","created":"2021-03-31","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":"2011.13148","title":"Streaming end-to-end multi-talker speech recognition","created":"2020-11-26","cited_by_count":29},{"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":"2307.11394","title":"MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems","created":"2023-07-21","cited_by_count":28},{"id":"1811.02062","title":"End-to-End Monaural Multi-speaker ASR System without Pretraining","created":"2018-11-05","cited_by_count":26},{"id":"2005.08072","title":"Speech Recognition and Multi-Speaker Diarization of Long Conversations","created":"2020-05-16","cited_by_count":23},{"id":"2110.03151","title":"Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR","created":"2021-10-07","cited_by_count":22},{"id":"2211.00482","title":"Adapting self-supervised models to multi-talker speech recognition using speaker embeddings","created":"2022-11-01","cited_by_count":18},{"id":"2204.10749","title":"E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR","created":"2022-04-22","cited_by_count":17},{"id":"2409.08596","title":"Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions","created":"2024-09-13","cited_by_count":17},{"id":"2303.16501","title":"AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR","created":"2023-03-29","cited_by_count":16},{"id":"2006.02786","title":"Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR","created":"2020-06-04","cited_by_count":15},{"id":"2302.09908","title":"A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One","created":"2023-02-20","cited_by_count":13},{"id":"2310.01688","title":"One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition","created":"2023-10-02","cited_by_count":12},{"id":"2011.02921","title":"Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR","created":"2020-11-03","cited_by_count":11},{"id":"2305.18747","title":"Adapting Multi-Lingual ASR Models for Handling Multiple Talkers","created":"2023-05-30","cited_by_count":11},{"id":"2407.09817","title":"Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System","created":"2024-07-13","cited_by_count":11},{"id":"2107.02852","title":"A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio","created":"2021-07-06","cited_by_count":10},{"id":"2210.15715","title":"Simulating realistic speech overlaps improves multi-talker ASR","created":"2022-10-27","cited_by_count":10},{"id":"2408.17431","title":"Advancing Multi-talker ASR Performance with Large Language Models","created":"2024-08-30","cited_by_count":10},{"id":"1908.04737","title":"End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning","created":"2019-08-13","cited_by_count":9},{"id":"2401.04152","title":"Cross-Speaker Encoding Network for Multi-Talker Speech Recognition","created":"2024-01-08","cited_by_count":9},{"id":"2101.01853","title":"Hypothesis Stitcher for End-to-End Speaker-attributed ASR on Long-form Multi-talker Recordings","created":"2021-01-06","cited_by_count":7},{"id":"2409.00815","title":"Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition","created":"2024-09-01","cited_by_count":7},{"id":"2305.12459","title":"CASA-ASR: Context-Aware Speaker-Attributed ASR","created":"2023-05-21","cited_by_count":6},{"id":"2403.02010","title":"SA-SOT: Speaker-Aware Serialized Output Training for Multi-Talker ASR","created":"2024-03-04","cited_by_count":6},{"id":"2203.16834","title":"A Comparative Study on Speaker-attributed Automatic Speech Recognition in Multi-party Meetings","created":"2022-03-31","cited_by_count":5},{"id":"2305.13716","title":"BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR","created":"2023-05-23","cited_by_count":5},{"id":"2406.06582","title":"Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing","created":"2024-06-04","cited_by_count":5},{"id":"2407.03966","title":"Serialized Output Training by Learned Dominance","created":"2024-07-04","cited_by_count":5},{"id":"2107.01549","title":"Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimation","created":"2021-07-04","cited_by_count":4},{"id":"2205.05206","title":"Best of Both Worlds: Multi-task Audio-Visual Automatic Speech Recognition and Active Speaker Detection","created":"2022-05-10","cited_by_count":4},{"id":"2409.00819","title":"LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization","created":"2024-09-01","cited_by_count":4},{"id":"2409.12352","title":"META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR","created":"2024-09-18","cited_by_count":4},{"id":"2409.12388","title":"Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC","created":"2024-09-19","cited_by_count":4},{"id":"2409.20301","title":"Alignment-Free Training for Transducer-based Multi-Talker ASR","created":"2024-09-30","cited_by_count":4},{"id":"2010.11803","title":"Compositional embedding models for speaker identification and diarization with simultaneous speech from 2+ speakers","created":"2020-10-22","cited_by_count":3},{"id":"2205.05586","title":"End-to-End Multi-Person Audio/Visual Automatic Speech Recognition","created":"2022-05-11","cited_by_count":3},{"id":"2205.05684","title":"A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection","created":"2022-05-11","cited_by_count":3},{"id":"2409.01438","title":"Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR","created":"2024-09-02","cited_by_count":3},{"id":"2109.04160","title":"Compositional Clustering: Applications to Multi-Label Object Recognition and Speaker Identification","created":"2021-09-09","cited_by_count":1},{"id":"2306.16398","title":"Cascaded encoders for fine-tuning ASR models on overlapped speech","created":"2023-06-28","cited_by_count":1},{"id":"2409.15732","title":"Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens","created":"2024-09-24","cited_by_count":1}],"next_cursor":null}