{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"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":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2008.10010","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","created":"2020-08-23","cited_by_count":672},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"1910.11480","title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","created":"2019-10-25","cited_by_count":340},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288},{"id":"1806.04558","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","created":"2018-06-12","cited_by_count":282},{"id":"2005.11129","title":"Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search","created":"2020-05-22","cited_by_count":273},{"id":"1905.03820","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","created":"2019-05-09","cited_by_count":252},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2312.15185","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","created":"2023-12-23","cited_by_count":205},{"id":"2006.12847","title":"Real Time Speech Enhancement in the Waveform Domain","created":"2020-06-23","cited_by_count":186},{"id":"2309.03199","title":"Matcha-TTS: A fast TTS architecture with conditional flow matching","created":"2023-09-06","cited_by_count":145},{"id":"2103.00993","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","created":"2021-03-01","cited_by_count":98},{"id":"2106.03153","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","created":"2021-06-06","cited_by_count":93},{"id":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87},{"id":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"2309.07937","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","created":"2023-09-14","cited_by_count":72},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41},{"id":"2203.09690","title":"A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing","created":"2022-03-18","cited_by_count":40},{"id":"2110.08243","title":"Neural Dubber: Dubbing for Videos According to Scripts","created":"2021-10-15","cited_by_count":39},{"id":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35},{"id":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29},{"id":"2012.07267","title":"Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis","created":"2020-12-14","cited_by_count":28},{"id":"2302.13700","title":"Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech","created":"2023-02-27","cited_by_count":27},{"id":"2111.12890","title":"V2C: Visual Voice Cloning","created":"2021-11-25","cited_by_count":24},{"id":"2306.03258","title":"LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading","created":"2023-06-05","cited_by_count":22},{"id":"2308.07787","title":"DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding","created":"2023-08-15","cited_by_count":22},{"id":"2302.08841","title":"Lip-to-Speech Synthesis in the Wild with Multi-task Learning","created":"2023-02-17","cited_by_count":21},{"id":"2402.12636","title":"StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing","created":"2024-02-20","cited_by_count":21},{"id":"2111.10139","title":"More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech","created":"2021-11-19","cited_by_count":12},{"id":"2407.15835","title":"dMel: Speech Tokenization made Simple","created":"2024-07-22","cited_by_count":11},{"id":"2204.01672","title":"Residual-guided Personalized Speech Synthesis based on Face Image","created":"2022-04-01","cited_by_count":10},{"id":"2205.07180","title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT","created":"2022-05-15","cited_by_count":8},{"id":"2006.06940","title":"Neural voice cloning with a few low-quality samples","created":"2020-06-12","cited_by_count":1}],"next_cursor":null}