{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"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":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"2006.13979","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","created":"2020-06-24","cited_by_count":501},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411},{"id":"1409.5185","title":"Deeply-Supervised Nets","created":"2014-09-18","cited_by_count":367},{"id":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"2003.08505","title":"A Metric Learning Reality Check","created":"2020-03-18","cited_by_count":321},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"2202.01855","title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition","created":"2022-02-03","cited_by_count":162},{"id":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110},{"id":"2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","created":"2020-11-23","cited_by_count":101},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101},{"id":"2308.05725","title":"EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis","created":"2023-08-10","cited_by_count":98},{"id":"2210.00077","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","created":"2022-09-30","cited_by_count":92},{"id":"2309.08105","title":"Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context","created":"2023-09-15","cited_by_count":85},{"id":"1910.12607","title":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","created":"2019-10-23","cited_by_count":82},{"id":"2305.08842","title":"Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks","created":"2023-05-15","cited_by_count":82},{"id":"2310.11230","title":"Zipformer: A faster and better encoder for automatic speech recognition","created":"2023-10-17","cited_by_count":80},{"id":"2204.09224","title":"ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers","created":"2022-04-20","cited_by_count":74},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71},{"id":"2005.08392","title":"Vector-Quantized Autoregressive Predictive Coding","created":"2020-05-17","cited_by_count":69},{"id":"2406.06371","title":"mHuBERT-147: A Compact Multilingual HuBERT Model","created":"2024-06-10","cited_by_count":66},{"id":"2407.00463","title":"Open-Source Conversational AI with SpeechBrain 1.0","created":"2024-06-29","cited_by_count":56},{"id":"2407.00837","title":"Towards Robust Speech Representation Learning for Thousands of Languages","created":"2024-06-30","cited_by_count":50},{"id":"2104.14700","title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","created":"2021-04-29","cited_by_count":47},{"id":"2301.00591","title":"Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling","created":"2023-01-02","cited_by_count":47},{"id":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39},{"id":"2305.10005","title":"DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning","created":"2023-05-17","cited_by_count":37},{"id":"2210.15759","title":"Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge","created":"2022-10-27","cited_by_count":34},{"id":"2203.16193","title":"Probing phoneme, language and speaker information in unsupervised speech representations","created":"2022-03-30","cited_by_count":33},{"id":"2404.00685","title":"Scaling Properties of Speech Language Models","created":"2024-03-31","cited_by_count":32},{"id":"2111.07402","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","created":"2021-11-14","cited_by_count":29},{"id":"2310.17864","title":"TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch","created":"2023-10-27","cited_by_count":27},{"id":"2302.12057","title":"ProsAudit, a prosodic benchmark for self-supervised speech models","created":"2023-02-23","cited_by_count":25},{"id":"2203.05936","title":"Are discrete units necessary for Spoken Language Modeling?","created":"2022-03-11","cited_by_count":24},{"id":"2409.07437","title":"Salmon: A Suite for Acoustic Language Model Evaluation","created":"2024-09-11","cited_by_count":24},{"id":"2410.04029","title":"SyllableLM: Learning Coarse Semantic Units for Speech Language Models","created":"2024-10-05","cited_by_count":24},{"id":"2305.11072","title":"Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering","created":"2023-05-18","cited_by_count":22},{"id":"2007.13542","title":"Evaluating the reliability of acoustic speech embeddings","created":"2020-07-27","cited_by_count":21},{"id":"2306.06672","title":"Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute","created":"2023-06-11","cited_by_count":21},{"id":"2305.12464","title":"Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces","created":"2023-05-21","cited_by_count":20},{"id":"2310.05224","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","created":"2023-10-08","cited_by_count":19},{"id":"2209.15483","title":"Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling","created":"2022-09-30","cited_by_count":17},{"id":"2310.02720","title":"Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction","created":"2023-10-04","cited_by_count":17},{"id":"2211.09944","title":"MelHuBERT: A simplified HuBERT on Mel spectrograms","created":"2022-11-17","cited_by_count":16},{"id":"2112.08778","title":"Self-Supervised Learning for speech recognition with Intermediate layer supervision","created":"2021-12-16","cited_by_count":15},{"id":"2504.02398","title":"Scaling Analysis of Interleaved Speech-Text Language Models","created":"2025-04-03","cited_by_count":14},{"id":"2406.11037","title":"NAST: Noise Aware Speech Tokenization for Speech Language Models","created":"2024-06-16","cited_by_count":13},{"id":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12},{"id":"2210.15775","title":"Evaluating context-invariance in unsupervised speech representations","created":"2022-10-27","cited_by_count":11},{"id":"2309.13860","title":"Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning","created":"2023-09-25","cited_by_count":9},{"id":"2409.06109","title":"Estimating the Completeness of Discrete Speech Units","created":"2024-09-09","cited_by_count":9},{"id":"2410.24177","title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models","created":"2024-10-31","cited_by_count":9},{"id":"1603.02845","title":"Unsupervised word segmentation and lexicon discovery using acoustic word embeddings","created":"2016-03-09","cited_by_count":8},{"id":"2203.15840","title":"Autoregressive Co-Training for Learning Discrete Speech Representations","created":"2022-03-29","cited_by_count":8},{"id":"2309.15317","title":"Joint Prediction and Denoising for Large-scale Multilingual Self-supervised Learning","created":"2023-09-26","cited_by_count":8},{"id":"2410.00025","title":"Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach","created":"2024-09-16","cited_by_count":8},{"id":"2311.09117","title":"R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces","created":"2023-11-15","cited_by_count":7},{"id":"2505.02692","title":"fastabx: A library for efficient computation of ABX discriminability","created":"2025-05-05","cited_by_count":7},{"id":"2411.17100","title":"k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning","created":"2024-11-26","cited_by_count":6},{"id":"2505.23494","title":"Spoken Language Modeling with Duration-Penalized Self-Supervised Units","created":"2025-05-29","cited_by_count":5},{"id":"2305.08099","title":"Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations","created":"2023-05-14","cited_by_count":4},{"id":"2410.13179","title":"EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning","created":"2024-10-17","cited_by_count":4}],"next_cursor":null}