{"list":"other","total":63,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1611.04076","title":"Least Squares Generative Adversarial Networks","created":"2016-11-13","cited_by_count":1001},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"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":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"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":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2106.06103","title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","created":"2021-06-11","cited_by_count":561},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"id":"2407.05407","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","created":"2024-07-07","cited_by_count":334},{"id":"2406.02430","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","created":"2024-06-04","cited_by_count":300},{"id":"2112.02418","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","created":"2021-12-04","cited_by_count":278},{"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":"2110.01763","title":"DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors","created":"2021-10-05","cited_by_count":172},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161},{"id":"2306.07691","title":"StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models","created":"2023-06-13","cited_by_count":152},{"id":"2505.17589","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","created":"2025-05-23","cited_by_count":150},{"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":"1808.10583","title":"AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale","created":"2018-08-31","cited_by_count":128},{"id":"2601.15621","title":"Qwen3-TTS Technical Report","created":"2026-01-22","cited_by_count":118},{"id":"2503.01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","created":"2025-03-03","cited_by_count":113},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72},{"id":"2502.04128","title":"Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis","created":"2025-02-06","cited_by_count":70},{"id":"2502.17239","title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","created":"2025-02-24","cited_by_count":68},{"id":"2512.23808","title":"MiMo-Audio: Audio Language Models are Few-Shot Learners","created":"2025-12-29","cited_by_count":65},{"id":"2305.07243","title":"Better speech synthesis through scaling","created":"2023-05-12","cited_by_count":63},{"id":"2411.19842","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","created":"2024-11-29","cited_by_count":49},{"id":"2305.16608","title":"AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec","created":"2023-05-26","cited_by_count":47},{"id":"2409.05377","title":"BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec","created":"2024-09-09","cited_by_count":46},{"id":"2309.07405","title":"FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec","created":"2023-09-14","cited_by_count":44},{"id":"2509.24650","title":"VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning","created":"2025-09-29","cited_by_count":42},{"id":"2308.12792","title":"Sparks of Large Audio Models: A Survey and Outlook","created":"2023-08-24","cited_by_count":41},{"id":"2402.13236","title":"Towards audio language modeling -- an overview","created":"2024-02-20","cited_by_count":40},{"id":"2312.11825","title":"MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation","created":"2023-12-19","cited_by_count":39},{"id":"2401.13527","title":"SpeechGPT-Gen: Scaling Chain-of-Information Speech Generation","created":"2024-01-24","cited_by_count":37},{"id":"2509.02020","title":"FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot","created":"2025-09-02","cited_by_count":35},{"id":"2409.09408","title":"Leveraging Self-Supervised Learning for Speaker Diarization","created":"2024-09-14","cited_by_count":23},{"id":"2506.23325","title":"XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs","created":"2025-06-29","cited_by_count":23},{"id":"2505.13000","title":"DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation","created":"2025-05-19","cited_by_count":21},{"id":"2503.01485","title":"FlowDec: A flow-based full-band general audio codec with high perceptual quality","created":"2025-03-03","cited_by_count":15},{"id":"2504.10344","title":"ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling","created":"2025-04-14","cited_by_count":12},{"id":"2505.24111","title":"Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization","created":"2025-05-30","cited_by_count":10},{"id":"2506.18623","title":"Efficient and Robust Speaker Diarization via Structured Pruning of Self-Supervised Models","created":"2025-06-23","cited_by_count":7},{"id":"2602.10934","title":"MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models","created":"2026-02-11","cited_by_count":6}],"next_cursor":null}