{"list":"other","total":76,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"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":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"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":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"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":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"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":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406},{"id":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"id":"2403.03100","title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","created":"2024-03-05","cited_by_count":226},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186},{"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":"1907.01160","title":"WHAM!: Extending Speech Separation to Noisy Environments","created":"2019-07-02","cited_by_count":156},{"id":"2005.11262","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","created":"2020-05-22","cited_by_count":155},{"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":"2412.09871","title":"Byte Latent Transformer: Patches Scale Better Than Tokens","created":"2024-12-13","cited_by_count":146},{"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":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112},{"id":"2211.09761","title":"Efficient Transformers with Dynamic Token Pooling","created":"2022-11-17","cited_by_count":76},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","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":"2305.18975","title":"Voice Conversion With Just Nearest Neighbors","created":"2023-05-30","cited_by_count":68},{"id":"1809.02403","title":"Deep Recurrent Survival Analysis","created":"2018-09-07","cited_by_count":61},{"id":"2407.00463","title":"Open-Source Conversational AI with SpeechBrain 1.0","created":"2024-06-29","cited_by_count":56},{"id":"2411.19842","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","created":"2024-11-29","cited_by_count":49},{"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":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43},{"id":"2506.10274","title":"Discrete Audio Tokens: More Than a Survey!","created":"2025-06-12","cited_by_count":38},{"id":"2312.09747","title":"SELM: Speech Enhancement Using Discrete Tokens and Language Models","created":"2023-12-15","cited_by_count":36},{"id":"2404.14408","title":"SpaceByte: Towards Deleting Tokenization from Large Language Modeling","created":"2024-04-22","cited_by_count":34},{"id":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32},{"id":"2407.08818","title":"MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization","created":"2024-07-11","cited_by_count":31},{"id":"2509.08753","title":"Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling","created":"2025-09-10","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":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24},{"id":"2406.10735","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","created":"2024-06-15","cited_by_count":24},{"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":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","cited_by_count":18},{"id":"2410.00168","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","created":"2024-09-30","cited_by_count":16},{"id":"2504.07053","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2025-04-09","cited_by_count":16},{"id":"2502.03382","title":"High-Fidelity Simultaneous Speech-To-Speech Translation","created":"2025-02-05","cited_by_count":15},{"id":"2506.14761","title":"From Bytes to Ideas: Language Modeling with Autoregressive U-Nets","created":"2025-06-17","cited_by_count":15},{"id":"2206.02211","title":"Variable-rate hierarchical CPC leads to acoustic unit discovery in speech","created":"2022-06-05","cited_by_count":13},{"id":"2508.16790","title":"TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling","created":"2025-08-22","cited_by_count":13},{"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":"2510.00981","title":"FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates","created":"2025-10-01","cited_by_count":10},{"id":"2410.24177","title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models","created":"2024-10-31","cited_by_count":9},{"id":"2502.15218","title":"ESPnet-SpeechLM: An Open Speech Language Model Toolkit","created":"2025-02-21","cited_by_count":9},{"id":"2509.16195","title":"FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation","created":"2025-09-19","cited_by_count":9},{"id":"2402.02754","title":"Focal Modulation Networks for Interpretable Sound Classification","created":"2024-02-05","cited_by_count":8},{"id":"2506.00385","title":"MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation","created":"2025-05-31","cited_by_count":7},{"id":"2505.14470","title":"PAST: Phonetic-Acoustic Speech Tokenizer","created":"2025-05-20","cited_by_count":6},{"id":"2412.01053","title":"FreeCodec: A disentangled neural speech codec with fewer tokens","created":"2024-12-02","cited_by_count":5},{"id":"2510.06195","title":"Latent Speech-Text Transformer","created":"2025-10-07","cited_by_count":5},{"id":"2505.16845","title":"Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate","created":"2025-05-22","cited_by_count":4},{"id":"2506.21074","title":"CodecSlime: Temporal Redundancy Compression of Neural Speech Codec via Dynamic Frame Rate","created":"2025-06-26","cited_by_count":4},{"id":"2509.04685","title":"Say More with Less: Variable-Frame-Rate Speech Tokenization via Adaptive Clustering and Implicit Duration Coding","created":"2025-09-04","cited_by_count":4},{"id":"2503.12115","title":"Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations","created":"2025-03-15","cited_by_count":3},{"id":"2510.14934","title":"TASLA: Text-Aligned Speech Tokens with Multiple Layer-Aggregation","created":"2025-10-16","cited_by_count":3}],"next_cursor":null}