{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"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":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"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":"2106.06909","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","created":"2021-06-13","cited_by_count":399},{"id":"2104.05938","title":"QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization","created":"2021-04-13","cited_by_count":365},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264},{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","cited_by_count":236},{"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":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126},{"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":"2207.02971","title":"Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding","created":"2022-07-06","cited_by_count":91},{"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":"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":"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":"1912.05533","title":"SpecAugment on Large Scale Datasets","created":"2019-12-11","cited_by_count":60},{"id":"2104.03603","title":"AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario","created":"2021-04-08","cited_by_count":60},{"id":"2105.03036","title":"SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts","created":"2021-05-07","cited_by_count":48},{"id":"2104.02138","title":"Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding","created":"2021-04-05","cited_by_count":42},{"id":"2109.12174","title":"Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations","created":"2021-09-24","cited_by_count":42},{"id":"2309.13876","title":"Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data","created":"2023-09-25","cited_by_count":42},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","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":"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":"1804.05053","title":"Voices Obscured in Complex Environmental Settings (VOICES) corpus","created":"2018-04-13","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":"1912.04979","title":"Advances in Online Audio-Visual Meeting Transcription","created":"2019-12-10","cited_by_count":23},{"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":"2210.13248","title":"Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation","created":"2022-10-24","cited_by_count":23},{"id":"2409.09408","title":"Leveraging Self-Supervised Learning for Speaker Diarization","created":"2024-09-14","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":"2401.08887","title":"NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription","created":"2024-01-16","cited_by_count":21},{"id":"2409.19898","title":"UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs","created":"2024-09-30","cited_by_count":21},{"id":"2010.03432","title":"WER we are and WER we think we are","created":"2020-10-07","cited_by_count":19},{"id":"2011.01997","title":"DOVER-Lap: A Method for Combining Overlap-aware Diarization Outputs","created":"2020-11-03","cited_by_count":19},{"id":"2203.14222","title":"Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition","created":"2022-03-27","cited_by_count":19},{"id":"2204.00540","title":"End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation","created":"2022-04-01","cited_by_count":17},{"id":"2401.03506","title":"DiarizationLM: Speaker Diarization Post-Processing with Large Language Models","created":"2024-01-07","cited_by_count":16},{"id":"2002.03577","title":"Accelerating RNN Transducer Inference via One-Step Constrained Beam Search","created":"2020-02-10","cited_by_count":13},{"id":"2303.03849","title":"TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings","created":"2023-03-07","cited_by_count":12},{"id":"1910.00716","title":"State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions","created":"2019-10-01","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":"2212.05271","title":"GPU-accelerated Guided Source Separation for Meeting Transcription","created":"2022-12-10","cited_by_count":10},{"id":"2409.09543","title":"Target Speaker ASR with Whisper","created":"2024-09-14","cited_by_count":9},{"id":"2406.08396","title":"Neural Blind Source Separation and Diarization for Distant Speech Recognition","created":"2024-06-12","cited_by_count":6},{"id":"2310.12371","title":"Property-Aware Multi-Speaker Data Simulation: A Probabilistic Modelling Technique for Synthetic Data Generation","created":"2023-10-18","cited_by_count":5},{"id":"2311.11353","title":"Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition","created":"2023-11-19","cited_by_count":5},{"id":"2309.12521","title":"Profile-Error-Tolerant Target-Speaker Voice Activity Detection","created":"2023-09-21","cited_by_count":4},{"id":"2406.18972","title":"Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over","created":"2024-06-27","cited_by_count":4},{"id":"2310.12378","title":"The CHiME-7 Challenge: System Description and Performance of NeMo Team's DASR System","created":"2023-10-18","cited_by_count":3}],"next_cursor":null}