{"list":"other","total":54,"rows":[{"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":"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":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"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":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"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":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406},{"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":"1709.05522","title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","created":"2017-09-16","cited_by_count":373},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"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":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2011.13205","title":"SLURP: A Spoken Language Understanding Resource Package","created":"2020-11-26","cited_by_count":198},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"2206.08317","title":"Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition","created":"2022-06-16","cited_by_count":144},{"id":"1808.10583","title":"AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale","created":"2018-08-31","cited_by_count":128},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"2305.11013","title":"FunASR: A Fundamental End-to-End Speech Recognition Toolkit","created":"2023-05-18","cited_by_count":95},{"id":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87},{"id":"1806.09514","title":"The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems","created":"2018-06-25","cited_by_count":61},{"id":"2203.15149","title":"CMGAN: Conformer-based Metric GAN for Speech Enhancement","created":"2022-03-28","cited_by_count":45},{"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":"2009.02095","title":"SEANet: A Multi-modal Speech Enhancement Network","created":"2020-09-04","cited_by_count":37},{"id":"2309.07377","title":"Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS","created":"2023-09-14","cited_by_count":24},{"id":"2306.02207","title":"SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts","created":"2023-06-03","cited_by_count":21},{"id":"2006.01713","title":"SAN-M: Memory Equipped Self-Attention for End-to-End Speech Recognition","created":"2020-05-21","cited_by_count":16},{"id":"2104.03575","title":"BSTC: A Large-Scale Chinese-English Speech Translation Dataset","created":"2021-04-08","cited_by_count":16},{"id":"2105.03070","title":"SpeechNet: A Universal Modularized Model for Speech Processing Tasks","created":"2021-05-07","cited_by_count":16},{"id":"2307.10757","title":"Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition","created":"2023-07-20","cited_by_count":16},{"id":"2306.15354","title":"3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement","created":"2023-06-27","cited_by_count":15},{"id":"2204.06812","title":"Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation","created":"2022-04-14","cited_by_count":13},{"id":"2209.09444","title":"Vega-MT: The JD Explore Academy Translation System for WMT22","created":"2022-09-20","cited_by_count":9},{"id":"2303.12984","title":"LMCodec: A Low Bitrate Speech Codec With Causal Transformer Models","created":"2023-03-23","cited_by_count":9},{"id":"2007.00225","title":"The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation","created":"2020-07-01","cited_by_count":8}],"next_cursor":null}