{"list":"other","total":63,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"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":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601},{"id":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"2006.13979","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","created":"2020-06-24","cited_by_count":501},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"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":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260},{"id":"2002.02562","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","created":"2020-02-07","cited_by_count":235},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231},{"id":"2312.05187","title":"Seamless: Multilingual Expressive and Streaming Speech Translation","created":"2023-12-08","cited_by_count":192},{"id":"2304.11127","title":"Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance","created":"2023-04-21","cited_by_count":147},{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140},{"id":"2208.12266","title":"Decoding speech perception from non-invasive brain recordings","created":"2022-08-25","cited_by_count":130},{"id":"2312.06550","title":"LLM360: Towards Fully Transparent Open-Source LLMs","created":"2023-12-11","cited_by_count":104},{"id":"2311.00430","title":"Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling","created":"2023-11-01","cited_by_count":90},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88},{"id":"2104.02133","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","created":"2021-04-05","cited_by_count":83},{"id":"2310.11230","title":"Zipformer: A faster and better encoder for automatic speech recognition","created":"2023-10-17","cited_by_count":80},{"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":"2305.11863","title":"Scaling laws for language encoding models in fMRI","created":"2023-05-19","cited_by_count":68},{"id":"2206.01685","title":"Toward a realistic model of speech processing in the brain with self-supervised learning","created":"2022-06-03","cited_by_count":63},{"id":"2104.14830","title":"Scaling End-to-End Models for Large-Scale Multilingual ASR","created":"2021-04-30","cited_by_count":61},{"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":"2403.20266","title":"Latxa: An Open Language Model and Evaluation Suite for Basque","created":"2024-03-29","cited_by_count":42},{"id":"2102.12664","title":"MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition","created":"2021-02-25","cited_by_count":39},{"id":"2110.04590","title":"An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition","created":"2021-10-09","cited_by_count":39},{"id":"1511.06066","title":"Transfer Learning for Speech and Language Processing","created":"2015-11-19","cited_by_count":35},{"id":"1808.05312","title":"Toward domain-invariant speech recognition via large scale training","created":"2018-08-16","cited_by_count":35},{"id":"2107.07903","title":"Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan","created":"2021-07-16","cited_by_count":26},{"id":"1701.02720","title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","created":"2017-01-10","cited_by_count":24},{"id":"2210.13352","title":"ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition","created":"2022-10-24","cited_by_count":18},{"id":"2211.05869","title":"A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding","created":"2022-11-10","cited_by_count":18},{"id":"2309.11756","title":"Sparsely Shared LoRA on Whisper for Child Speech Recognition","created":"2023-09-21","cited_by_count":18},{"id":"2407.07595","title":"Scaling Law in Neural Data: Non-Invasive Speech Decoding with 175 Hours of EEG Data","created":"2024-07-10","cited_by_count":13},{"id":"2110.12201","title":"Spanish Legalese Language Model and Corpora","created":"2021-10-23","cited_by_count":11},{"id":"2203.08111","title":"Does Corpus Quality Really Matter for Low-Resource Languages?","created":"2022-03-15","cited_by_count":11},{"id":"2305.10788","title":"DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition","created":"2023-05-18","cited_by_count":11},{"id":"2412.15726","title":"Fine-tuning Whisper on Low-Resource Languages for Real-World Applications","created":"2024-12-20","cited_by_count":11},{"id":"2304.11075","title":"Spaiche: Extending State-of-the-Art ASR Models to Swiss German Dialects","created":"2023-04-20","cited_by_count":8},{"id":"2305.13026","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","created":"2023-05-22","cited_by_count":6},{"id":"2409.16954","title":"Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition","created":"2024-09-25","cited_by_count":6},{"id":"2102.07259","title":"Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition","created":"2021-02-14","cited_by_count":5},{"id":"2105.04674","title":"What shall we do with an hour of data? Speech recognition for the un- and under-served languages of Common Voice","created":"2021-05-10","cited_by_count":5},{"id":"2406.13893","title":"Open Generative Large Language Models for Galician","created":"2024-06-19","cited_by_count":3}],"next_cursor":null}