{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"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":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"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":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"2006.04558","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","created":"2020-06-08","cited_by_count":717},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"2406.02430","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","created":"2024-06-04","cited_by_count":300},{"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":"2302.03540","title":"Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision","created":"2023-02-07","cited_by_count":169},{"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":"2406.18009","title":"E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS","created":"2024-06-26","cited_by_count":152},{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140},{"id":"2502.05139","title":"Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound","created":"2025-02-07","cited_by_count":137},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126},{"id":"2308.11596","title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","created":"2023-08-22","cited_by_count":125},{"id":"2406.05370","title":"VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers","created":"2024-06-08","cited_by_count":122},{"id":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87},{"id":"2402.08093","title":"BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data","created":"2024-02-12","cited_by_count":75},{"id":"2207.01063","title":"DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech","created":"2022-07-03","cited_by_count":69},{"id":"2407.08551","title":"Autoregressive Speech Synthesis without Vector Quantization","created":"2024-07-11","cited_by_count":65},{"id":"2401.07333","title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering","created":"2024-01-14","cited_by_count":50},{"id":"2005.10438","title":"Conversational End-to-End TTS for Voice Agent","created":"2020-05-21","cited_by_count":37},{"id":"2306.07547","title":"UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding","created":"2023-06-13","cited_by_count":37},{"id":"2201.03967","title":"Emotion Intensity and its Control for Emotional Voice Conversion","created":"2022-01-10","cited_by_count":35},{"id":"2509.02020","title":"FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot","created":"2025-09-02","cited_by_count":35},{"id":"2511.09690","title":"Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages","created":"2025-11-12","cited_by_count":34},{"id":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29},{"id":"2508.19205","title":"VibeVoice Technical Report","created":"2025-08-26","cited_by_count":29},{"id":"2305.19269","title":"Make-A-Voice: Unified Voice Synthesis With Discrete Representation","created":"2023-05-30","cited_by_count":27},{"id":"2404.03204","title":"RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis","created":"2024-04-04","cited_by_count":26},{"id":"2001.06785","title":"From Speech-to-Speech Translation to Automatic Dubbing","created":"2020-01-19","cited_by_count":25},{"id":"2406.07803","title":"EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech","created":"2024-06-12","cited_by_count":24},{"id":"1910.01709","title":"Semi-Supervised Generative Modeling for Controllable Speech Synthesis","created":"2019-10-03","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":"1906.10859","title":"End-to-End Emotional Speech Synthesis Using Style Tokens and Semi-Supervised Training","created":"2019-06-26","cited_by_count":19},{"id":"2310.01088","title":"Towards human-like spoken dialogue generation between AI agents from written dialogue","created":"2023-10-02","cited_by_count":19},{"id":"2411.02625","title":"EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector","created":"2024-11-04","cited_by_count":19},{"id":"2503.14345","title":"MoonCast: High-Quality Zero-Shot Podcast Generation","created":"2025-03-18","cited_by_count":18},{"id":"2407.21491","title":"Generative Expressive Conversational Speech Synthesis","created":"2024-07-31","cited_by_count":16},{"id":"2011.03530","title":"Large-scale multilingual audio visual dubbing","created":"2020-11-06","cited_by_count":15},{"id":"2404.06690","title":"CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations","created":"2024-04-10","cited_by_count":15},{"id":"2111.04730","title":"Emotional Prosody Control for Speech Generation","created":"2021-11-07","cited_by_count":12},{"id":"2504.02386","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","created":"2025-04-03","cited_by_count":11},{"id":"2210.15360","title":"FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis","created":"2022-10-27","cited_by_count":9},{"id":"2409.16681","title":"Emotional Dimension Control in Language Model-Based Text-to-Speech: Spanning a Broad Spectrum of Human Emotions","created":"2024-09-25","cited_by_count":8},{"id":"2405.09171","title":"Hierarchical Emotion Prediction and Control in Text-to-Speech Synthesis","created":"2024-05-15","cited_by_count":7},{"id":"2501.00805","title":"SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation","created":"2025-01-01","cited_by_count":6},{"id":"2412.12498","title":"Hierarchical Control of Emotion Rendering in Speech Synthesis","created":"2024-12-17","cited_by_count":3},{"id":"2211.06160","title":"Semi-supervised learning for continuous emotional intensity controllable speech synthesis with disentangled representations","created":"2022-11-11","cited_by_count":2}],"next_cursor":null}