{"list":"other","total":81,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"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":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1511.06709","title":"Improving Neural Machine Translation Models with Monolingual Data","created":"2015-11-20","cited_by_count":788},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"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":"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":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"2312.15185","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","created":"2023-12-23","cited_by_count":205},{"id":"2312.05187","title":"Seamless: Multilingual Expressive and Streaming Speech Translation","created":"2023-12-08","cited_by_count":192},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181},{"id":"2303.03926","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","created":"2023-03-07","cited_by_count":167},{"id":"1612.00370","title":"Improved Image Captioning via Policy Gradient optimization of SPIDEr","created":"2016-12-01","cited_by_count":113},{"id":"2104.02194","title":"Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion","created":"2021-04-05","cited_by_count":101},{"id":"2005.03191","title":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","created":"2020-05-07","cited_by_count":97},{"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":"2402.08846","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","created":"2024-02-13","cited_by_count":88},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84},{"id":"2307.16372","title":"LP-MusicCaps: LLM-Based Pseudo Music Captioning","created":"2023-07-31","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":"2501.01108","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","created":"2025-01-02","cited_by_count":68},{"id":"2306.12420","title":"LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models","created":"2023-06-21","cited_by_count":60},{"id":"2412.15649","title":"SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training","created":"2024-12-20","cited_by_count":59},{"id":"2401.03497","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","created":"2024-01-07","cited_by_count":53},{"id":"2311.03318","title":"A Foundation Model for Music Informatics","created":"2023-11-06","cited_by_count":46},{"id":"2309.08730","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","created":"2023-09-15","cited_by_count":45},{"id":"2007.05916","title":"The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results","created":"2020-07-12","cited_by_count":44},{"id":"2406.11546","title":"GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement","created":"2024-06-17","cited_by_count":34},{"id":"2110.04684","title":"Can Audio Captions Be Evaluated with Image Caption Metrics?","created":"2021-10-10","cited_by_count":33},{"id":"2312.10381","title":"SECap: Speech Emotion Captioning with Large Language Model","created":"2023-12-16","cited_by_count":33},{"id":"2305.12493","title":"Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network","created":"2023-05-21","cited_by_count":31},{"id":"2104.04214","title":"What is the ground truth? Reliability of multi-annotator data for audio tagging","created":"2021-04-09","cited_by_count":29},{"id":"2401.17690","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","created":"2024-01-31","cited_by_count":28},{"id":"2104.11984","title":"MusCaps: Generating Captions for Music Audio","created":"2021-04-24","cited_by_count":23},{"id":"2309.05396","title":"SlideSpeech: A Large-Scale Slide-Enriched Audio-Visual Corpus","created":"2023-09-11","cited_by_count":19},{"id":"2401.10449","title":"Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search","created":"2024-01-19","cited_by_count":19},{"id":"2404.03608","title":"Sailor: Open Language Models for South-East Asia","created":"2024-04-04","cited_by_count":19},{"id":"2411.06437","title":"CTC-Assisted LLM-Based Contextual ASR","created":"2024-11-10","cited_by_count":19},{"id":"2207.00857","title":"Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition","created":"2022-07-02","cited_by_count":17},{"id":"2401.08835","title":"Improving ASR Contextual Biasing with Guided Attention","created":"2024-01-16","cited_by_count":17},{"id":"2410.09503","title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","created":"2024-10-12","cited_by_count":15},{"id":"2406.13275","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","created":"2024-06-19","cited_by_count":14},{"id":"2312.09582","title":"Phoneme-aware Encoding for Prefix-tree-based Contextual ASR","created":"2023-12-15","cited_by_count":13},{"id":"2406.12707","title":"Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction","created":"2024-06-18","cited_by_count":13},{"id":"2410.09472","title":"DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning","created":"2024-10-12","cited_by_count":11},{"id":"2402.16124","title":"AVI-Talking: Learning Audio-Visual Instructions for Expressive 3D Talking Face Generation","created":"2024-02-25","cited_by_count":9},{"id":"2405.19041","title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","created":"2024-05-29","cited_by_count":9},{"id":"2309.12242","title":"Weakly-supervised Automated Audio Captioning via text only training","created":"2023-09-21","cited_by_count":8},{"id":"2402.09585","title":"Domain Adaptation for Contrastive Audio-Language Models","created":"2024-02-14","cited_by_count":8},{"id":"2406.06295","title":"Zero-Shot Audio Captioning Using Soft and Hard Prompts","created":"2024-06-10","cited_by_count":7},{"id":"2401.06390","title":"LCB-net: Long-Context Biasing for Audio-Visual Speech Recognition","created":"2024-01-12","cited_by_count":6}],"next_cursor":null}