{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"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":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"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":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608},{"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":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"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":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2408.16725","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","created":"2024-08-29","cited_by_count":210},{"id":"2307.03917","title":"On decoder-only architecture for speech-to-text and large language model integration","created":"2023-07-08","cited_by_count":145},{"id":"2307.11795","title":"Prompting Large Language Models with Speech Recognition Abilities","created":"2023-07-21","cited_by_count":140},{"id":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109},{"id":"1909.12406","title":"Monotonic Multihead Attention","created":"2019-09-26","cited_by_count":93},{"id":"2402.08846","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","created":"2024-02-13","cited_by_count":88},{"id":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87},{"id":"1704.00784","title":"Online and Linear-Time Attention by Enforcing Monotonic Alignments","created":"2017-04-03","cited_by_count":85},{"id":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80},{"id":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63},{"id":"2311.06753","title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","created":"2023-11-12","cited_by_count":59},{"id":"2308.15930","title":"LLaSM: Large Language and Speech Model","created":"2023-08-30","cited_by_count":58},{"id":"2401.13527","title":"SpeechGPT-Gen: Scaling Chain-of-Information Speech Generation","created":"2024-01-24","cited_by_count":37},{"id":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32},{"id":"2305.03101","title":"Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks","created":"2023-05-04","cited_by_count":20},{"id":"1911.02750","title":"Incremental Text-to-Speech Synthesis with Prefix-to-Prefix Framework","created":"2019-11-07","cited_by_count":15},{"id":"2406.09569","title":"Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time","created":"2024-06-13","cited_by_count":15},{"id":"2310.14883","title":"Non-autoregressive Streaming Transformer for Simultaneous Translation","created":"2023-10-23","cited_by_count":12},{"id":"2407.15415","title":"LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models","created":"2024-07-22","cited_by_count":12},{"id":"2312.03668","title":"Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition","created":"2023-12-06","cited_by_count":10},{"id":"2406.06937","title":"A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation","created":"2024-06-11","cited_by_count":10},{"id":"2009.02035","title":"What the Future Brings: Investigating the Impact of Lookahead for Incremental Neural TTS","created":"2020-09-04","cited_by_count":9},{"id":"2309.11210","title":"Speak While You Think: Streaming Speech Synthesis During Text Generation","created":"2023-09-20","cited_by_count":8},{"id":"2012.12612","title":"Incremental Text-to-Speech Synthesis Using Pseudo Lookahead with Large Pretrained Language Model","created":"2020-12-23","cited_by_count":7},{"id":"2310.17940","title":"Unified Segment-to-Segment Framework for Simultaneous Sequence Generation","created":"2023-10-27","cited_by_count":6},{"id":"2110.08214","title":"From Start to Finish: Latency Reduction Strategies for Incremental Speech Synthesis in Simultaneous Speech-to-Speech Translation","created":"2021-10-15","cited_by_count":3},{"id":"2109.10724","title":"Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network","created":"2021-09-22","cited_by_count":2},{"id":"2406.06910","title":"Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models","created":"2024-06-11","cited_by_count":2}],"next_cursor":null}