{"list":"other","total":54,"rows":[{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"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":"2304.09116","title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","created":"2023-04-18","cited_by_count":235},{"id":"2412.02612","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","created":"2024-12-03","cited_by_count":224},{"id":"2306.00814","title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","created":"2023-06-01","cited_by_count":153},{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129},{"id":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126},{"id":"2305.02765","title":"HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec","created":"2023-05-04","cited_by_count":97},{"id":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87},{"id":"2505.02625","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","created":"2025-05-05","cited_by_count":76},{"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":"2502.17239","title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","created":"2025-02-24","cited_by_count":68},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50},{"id":"2407.00837","title":"Towards Robust Speech Representation Learning for Thousands of Languages","created":"2024-06-30","cited_by_count":50},{"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":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","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":"2410.14411","title":"SNAC: Multi-Scale Neural Audio Codec","created":"2024-10-18","cited_by_count":43},{"id":"1602.03609","title":"Attentive Pooling Networks","created":"2016-02-11","cited_by_count":28},{"id":"2309.00169","title":"RepCodec: A Speech Representation Codec for Speech Tokenization","created":"2023-08-31","cited_by_count":27},{"id":"2411.18803","title":"TS3-Codec: Transformer-Based Simple Streaming Single Codec","created":"2024-11-27","cited_by_count":25},{"id":"2406.07422","title":"Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation","created":"2024-06-11","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":"2310.00014","title":"Fewer-token Neural Speech Codec with Time-invariant Codes","created":"2023-09-15","cited_by_count":22},{"id":"2406.10056","title":"UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner","created":"2024-06-14","cited_by_count":22},{"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":"2508.05835","title":"NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference","created":"2025-08-07","cited_by_count":15},{"id":"2211.11960","title":"Disentangled Feature Learning for Real-Time Neural Speech Coding","created":"2022-11-22","cited_by_count":10},{"id":"2510.00981","title":"FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates","created":"2025-10-01","cited_by_count":10},{"id":"2405.04752","title":"HILCodec: High-Fidelity and Lightweight Neural Audio Codec","created":"2024-05-08","cited_by_count":9},{"id":"2406.09869","title":"MMM: Multi-Layer Multi-Residual Multi-Stream Discrete Speech Representation from Self-supervised Learning Model","created":"2024-06-14","cited_by_count":9},{"id":"2510.16841","title":"SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization","created":"2025-10-19","cited_by_count":8},{"id":"2401.12160","title":"ScoreDec: A Phase-preserving High-Fidelity Audio Codec with A Generalized Score-based Diffusion Post-filter","created":"2024-01-22","cited_by_count":7},{"id":"2402.12208","title":"Language-Codec: Bridging Discrete Codec Representations and Speech Language Models","created":"2024-02-19","cited_by_count":6},{"id":"2409.08805","title":"Exploring SSL Discrete Tokens for Multilingual ASR","created":"2024-09-13","cited_by_count":6},{"id":"2410.06016","title":"Variable Bitrate Residual Vector Quantization for Audio Coding","created":"2024-10-08","cited_by_count":6},{"id":"2505.14470","title":"PAST: Phonetic-Acoustic Speech Tokenizer","created":"2025-05-20","cited_by_count":6},{"id":"2210.13700","title":"Does Joint Training Really Help Cascaded Speech Translation?","created":"2022-10-24","cited_by_count":5},{"id":"2411.00464","title":"MDCTCodec: A Lightweight MDCT-based Neural Audio Codec towards High Sampling Rate and Low Bitrate Scenarios","created":"2024-11-01","cited_by_count":4},{"id":"2505.16845","title":"Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate","created":"2025-05-22","cited_by_count":4},{"id":"2502.02019","title":"ComplexDec: A Domain-robust High-fidelity Neural Audio Codec with Complex Spectrum Modeling","created":"2025-02-04","cited_by_count":3},{"id":"2406.08905","title":"SingOMD: Singing Oriented Multi-resolution Discrete Representation Construction from Speech Models","created":"2024-06-13","cited_by_count":2},{"id":"2510.15364","title":"LDCodec: A high quality neural audio codec with low-complexity decoder","created":"2025-10-17","cited_by_count":1},{"id":"2511.22687","title":"PURE Codec: Progressive Unfolding of Residual Entropy for Speech Codec Learning","created":"2025-11-27","cited_by_count":1}],"next_cursor":null}