{"list":"other","total":72,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"1609.06773","title":"Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning","created":"2016-09-21","cited_by_count":257},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152},{"id":"1808.02480","title":"Deep context: end-to-end contextual speech recognition","created":"2018-08-07","cited_by_count":137},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129},{"id":"2102.01547","title":"WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit","created":"2021-02-02","cited_by_count":125},{"id":"2103.10022","title":"Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE","created":"2021-03-18","cited_by_count":106},{"id":"2104.02194","title":"Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion","created":"2021-04-05","cited_by_count":101},{"id":"2305.02765","title":"HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec","created":"2023-05-04","cited_by_count":97},{"id":"2006.03411","title":"Contextual RNN-T For Open Domain ASR","created":"2020-06-04","cited_by_count":85},{"id":"2011.01991","title":"Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition","created":"2020-11-03","cited_by_count":80},{"id":"2310.09424","title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","created":"2023-10-13","cited_by_count":76},{"id":"2002.11268","title":"A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition","created":"2020-02-26","cited_by_count":73},{"id":"2309.15649","title":"Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting","created":"2023-09-27","cited_by_count":72},{"id":"2310.00230","title":"SLM: Bridge the thin gap between speech and text foundation models","created":"2023-09-30","cited_by_count":67},{"id":"2011.07754","title":"Deep Shallow Fusion for RNN-T Personalization","created":"2020-11-16","cited_by_count":64},{"id":"1902.07178","title":"A spelling correction model for end-to-end speech recognition","created":"2019-02-19","cited_by_count":63},{"id":"2205.13660","title":"Contextual Adapters for Personalized Speech Recognition in Neural Transducers","created":"2022-05-26","cited_by_count":57},{"id":"2111.03250","title":"Context-Aware Transformer Transducer for Speech Recognition","created":"2021-11-05","cited_by_count":56},{"id":"1805.11063","title":"Theory and Experiments on Vector Quantized Autoencoders","created":"2018-05-28","cited_by_count":55},{"id":"2005.08520","title":"Robust Training of Vector Quantized Bottleneck Models","created":"2020-05-18","cited_by_count":54},{"id":"2201.12806","title":"Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection","created":"2022-01-30","cited_by_count":39},{"id":"2402.12654","title":"OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification","created":"2024-02-20","cited_by_count":37},{"id":"2202.01094","title":"RescoreBERT: Discriminative Speech Recognition Rescoring with BERT","created":"2022-02-02","cited_by_count":34},{"id":"2109.00627","title":"Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition","created":"2021-09-01","cited_by_count":32},{"id":"2305.12493","title":"Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network","created":"2023-05-21","cited_by_count":31},{"id":"1810.12170","title":"Contextual Speech Recognition with Difficult Negative Training Examples","created":"2018-10-29","cited_by_count":28},{"id":"2110.02220","title":"Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition","created":"2021-10-05","cited_by_count":25},{"id":"2309.10917","title":"End-to-End Speech Recognition Contextualization with Large Language Models","created":"2023-09-19","cited_by_count":22},{"id":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22},{"id":"2309.07414","title":"PromptASR for contextualized ASR with controllable style","created":"2023-09-14","cited_by_count":19},{"id":"2401.10449","title":"Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search","created":"2024-01-19","cited_by_count":19},{"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":"2211.01438","title":"Variable Attention Masking for Configurable Transformer Transducer Speech Recognition","created":"2022-11-02","cited_by_count":14},{"id":"2305.12839","title":"CopyNE: Better Contextual ASR by Copying Named Entities","created":"2023-05-22","cited_by_count":14},{"id":"1712.01864","title":"No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models","created":"2017-12-05","cited_by_count":13},{"id":"2301.06735","title":"Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducer","created":"2023-01-17","cited_by_count":12},{"id":"2210.16663","title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","created":"2022-10-29","cited_by_count":11},{"id":"2407.10303","title":"Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation","created":"2024-07-14","cited_by_count":11},{"id":"2302.08917","title":"Massively Multilingual Shallow Fusion with Large Language Models","created":"2023-02-17","cited_by_count":10},{"id":"2409.15353","title":"Contextualization of ASR with LLM using phonetic retrieval-based augmentation","created":"2024-09-11","cited_by_count":10},{"id":"2306.07944","title":"Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding","created":"2023-06-08","cited_by_count":9},{"id":"2304.08862","title":"Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition","created":"2023-04-18","cited_by_count":8},{"id":"2312.13560","title":"kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels","created":"2023-12-21","cited_by_count":8},{"id":"2311.08402","title":"Retrieve and Copy: Scaling ASR Personalization to Large Catalogs","created":"2023-11-14","cited_by_count":7},{"id":"2404.10180","title":"Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR","created":"2024-04-15","cited_by_count":5},{"id":"2303.10942","title":"On-the-fly Text Retrieval for End-to-End ASR Adaptation","created":"2023-03-20","cited_by_count":4},{"id":"2406.09618","title":"Multi-Modal Retrieval For Large Language Model Based Speech Recognition","created":"2024-06-13","cited_by_count":4},{"id":"2401.07360","title":"Promptformer: Prompted Conformer Transducer for ASR","created":"2024-01-14","cited_by_count":3},{"id":"2401.13146","title":"Locality enhanced dynamic biasing and sampling strategies for contextual ASR","created":"2024-01-23","cited_by_count":3},{"id":"2406.02921","title":"Text Injection for Neural Contextual Biasing","created":"2024-06-05","cited_by_count":3},{"id":"2304.01905","title":"Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition","created":"2023-04-03","cited_by_count":2}],"next_cursor":null}