{"total":90,"rows":[{"id":"2502.01549","title":"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos","created":"2025-02-03","cited_by_count":77,"area":"rag"},{"id":"2401.16658","title":"OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer","created":"2024-01-30","cited_by_count":74,"area":null},{"id":"2512.02425","title":"WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning","created":"2025-12-02","cited_by_count":53,"area":"lr"},{"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,"area":null},{"id":"2509.08753","title":"Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling","created":"2025-09-10","cited_by_count":27,"area":null},{"id":"2510.06961","title":"Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation","created":"2025-10-08","cited_by_count":23,"area":null},{"id":"2503.04713","title":"Scaling Rich Style-Prompted Text-to-Speech Datasets","created":"2025-03-06","cited_by_count":19,"area":null},{"id":"2502.12414","title":"Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2406.10447","title":"The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences","created":"2024-06-14","cited_by_count":17,"area":null},{"id":"2412.03512","title":"Distillation of Diffusion Features for Semantic Correspondence","created":"2024-12-04","cited_by_count":17,"area":null},{"id":"2504.07053","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2025-04-09","cited_by_count":16,"area":null},{"id":"2505.12969","title":"Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down","created":"2025-05-19","cited_by_count":12,"area":null},{"id":"2502.03945","title":"Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond","created":"2025-02-06","cited_by_count":11,"area":null},{"id":"2503.05931","title":"Training and Inference Efficiency of Encoder-Decoder Speech Models","created":"2025-03-07","cited_by_count":8,"area":null},{"id":"2411.05945","title":"NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model","created":"2024-11-08","cited_by_count":7,"area":"moe"},{"id":"2502.20583","title":"LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2506.07600","title":"SceneRAG: Scene-level Retrieval-Augmented Generation for Video Understanding","created":"2025-06-09","cited_by_count":7,"area":"rag"},{"id":"2506.18623","title":"Efficient and Robust Speaker Diarization via Structured Pruning of Self-Supervised Models","created":"2025-06-23","cited_by_count":7,"area":"distill"},{"id":"2408.03561","title":"MPC-Minimized Secure LLM Inference","created":"2024-08-07","cited_by_count":6,"area":null},{"id":"2409.15869","title":"Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR","created":"2024-09-24","cited_by_count":6,"area":null},{"id":"2407.10603","title":"Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data","created":"2024-07-15","cited_by_count":5,"area":"distill"},{"id":"2503.23542","title":"Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2505.20237","title":"Efficient Speech Translation through Model Compression and Knowledge Distillation","created":"2025-05-26","cited_by_count":5,"area":"distill"},{"id":"2402.01917","title":"Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2406.04512","title":"To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation","created":"2024-06-06","cited_by_count":4,"area":"distill"},{"id":"2406.15284","title":"The Greek podcast corpus: Competitive speech models for low-resourced languages with weakly supervised data","created":"2024-06-21","cited_by_count":4,"area":null},{"id":"2407.01257","title":"uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes","created":"2024-07-01","cited_by_count":4,"area":"distill"},{"id":"2510.08599","title":"BaldWhisper: Faster Whisper with Head Shearing and Layer Merging","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2510.22763","title":"Iterative Layer Pruning for Efficient Translation Inference","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2406.11022","title":"Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models","created":"2024-06-16","cited_by_count":3,"area":"distill"},{"id":"2409.15350","title":"A Large Dataset of Spontaneous Speech with the Accent Spoken in S\\~ao Paulo for Automatic Speech Recognition Evaluation","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2411.17426","title":"CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2412.15655","title":"MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2506.08846","title":"Addressing Pitfalls in Auditing Practices of Automatic Speech Recognition Technologies: A Case Study of People with Aphasia","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2507.02911","title":"DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective","created":"2025-06-25","cited_by_count":3,"area":"distill"},{"id":"2508.02801","title":"Adaptive Knowledge Distillation for Device-Directed Speech Detection","created":"2025-08-04","cited_by_count":3,"area":"distill"},{"id":"2511.18824","title":"Assessing the alignment between infants' visual and linguistic experience using multimodal language models","created":"2025-11-24","cited_by_count":3,"area":"mllm"},{"id":"2406.11016","title":"Optimized Speculative Sampling for GPU Hardware Accelerators","created":"2024-06-16","cited_by_count":2,"area":"inference"},{"id":"2409.17353","title":"Internalizing ASR with Implicit Chain of Thought for Efficient Speech-to-Speech Conversational LLM","created":"2024-09-25","cited_by_count":2,"area":"lr"},{"id":"2410.17901","title":"ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigrams","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2502.12408","title":"On the Robust Approximation of ASR Metrics","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2506.00145","title":"Vedavani: A Benchmark Corpus for ASR on Vedic Sanskrit Poetry","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2506.15912","title":"Early Attentive Sparsification Accelerates Neural Speech Transcription","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2506.23670","title":"Efficient Interleaved Speech Modeling through Knowledge Distillation","created":"2025-06-30","cited_by_count":2,"area":"distill"},{"id":"2507.18352","title":"Tiny is not small enough: High-quality, low-resource facial animation models through hybrid knowledge distillation","created":"2025-07-24","cited_by_count":2,"area":"distill"},{"id":"2510.09266","title":"CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation","created":"2025-10-10","cited_by_count":2,"area":"mllm"},{"id":"2510.16387","title":"Probing the Hidden Talent of ASR Foundation Models for L2 English Oral Assessment","created":"2025-10-18","cited_by_count":2,"area":null},{"id":"2510.19471","title":"Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2602.09373","title":"AfriNLLB: Efficient Translation Models for African Languages","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2603.27981","title":"On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2607.12463","title":"Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models","created":"2026-07-14","cited_by_count":2,"area":"agents"},{"id":"2405.01004","title":"Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2406.10034","title":"Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2409.13499","title":"Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper","created":"2024-09-20","cited_by_count":1,"area":"distill"},{"id":"2506.03722","title":"MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognition","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2507.03343","title":"SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge","created":"2025-07-04","cited_by_count":1,"area":null},{"id":"2507.12252","title":"Improving Contextual ASR via Multi-grained Fusion with Large Language Models","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2601.19919","title":"ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition","created":"2026-01-08","cited_by_count":1,"area":"distill"},{"id":"2602.18568","title":"RPU -- A Reasoning Processing Unit","created":"2026-02-20","cited_by_count":1,"area":"lr"},{"id":"2605.28139","title":"Data-Efficient On-Policy Distillation for Automatic Speech Recognition","created":"2026-05-27","cited_by_count":1,"area":"distill"},{"id":"2607.05365","title":"SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.21430","title":"Evaluating Multimodal Narrative Understanding of Popular Hollywood Films","created":"2026-08-17","cited_by_count":1,"area":"mllm"},{"id":"2406.08904","title":"AdaPTwin: Low-Cost Adaptive Compression of Product Twins in Transformers","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2503.22692","title":"Enhancing Aviation Communication Transcription: Fine-Tuning Distil-Whisper with LoRA","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2507.21522","title":"Model-free Speculative Decoding for Transformer-based ASR with Token Map Drafting","created":"2025-07-29","cited_by_count":0,"area":"inference"},{"id":"2508.11189","title":"Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2509.19271","title":"WolBanking77: Wolof Banking Speech Intent Classification Dataset","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2601.13704","title":"Performance and Complexity Trade-off Optimization of Speech Models During Training","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2603.05121","title":"Measuring the Redundancy of Decoder Layers in SpeechLLMs","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.10324","title":"NasoVoce: A Nose-Mounted Low-Audibility Speech Interface for Always-Available Speech Interaction","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.15326","title":"Tagarela - A Portuguese speech dataset from podcasts","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.08819","title":"SenBen: Sensitive Scene Graphs for Explainable Content Moderation","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.26136","title":"One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.03073","title":"The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.17710","title":"Sometin Beta Pass Notin: Improving Multilingual ASR for Nigerian Languages via Knowledge Distillation","created":"2026-05-18","cited_by_count":0,"area":"distill"},{"id":"2606.00771","title":"Logit Distillation on Manifolds: Mapping by Learning","created":"2026-05-30","cited_by_count":0,"area":"distill"},{"id":"2606.01483","title":"MURMUR: An Efficient Inference System for Long-Form ASR","created":"2026-05-31","cited_by_count":0,"area":"inference"},{"id":"2606.24758","title":"CANDLE: CTC-based Arabic Noisy-character Deduplication using a Lightweight Encoder","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.08256","title":"Best-of-$N$ TTS Evaluation is Confounded by ASR Family Alignment","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.17452","title":"How Reliable Are Multimodal Signals of Conversational State? Evidence from Remote Dyadic Collaborative Tasks","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.30927","title":"Stride-k Subsampling: Train-Free Audio Token Reduction for Whisper","created":"2026-08-31","cited_by_count":0,"area":"inference"},{"id":"2609.01737","title":"SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.11412","title":"X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation","created":"2026-09-10","cited_by_count":0,"area":"distill"},{"id":"2609.13151","title":"Token Merging for Multilingual Speech Recognition: A Systematic Study Across Model Scale and Fine-Tuning","created":"2026-07-07","cited_by_count":0,"area":"inference"},{"id":"2609.27289","title":"Ruby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognition","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.27980","title":"Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28739","title":"Temporal Taxation Compounds Under Post-Training Compression of Whisper Models","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.32560","title":"How to Reduce Whisper Hallucination","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.38897","title":"FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.19134","title":"CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition","created":"2026-10-13","cited_by_count":0,"area":"distill"}],"next_cursor":null}