Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
The AudioMOS Challenge 2025Meta · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)13 citationsDec 6, 2025Less is More: Data Curation Matters in Scaling Speech EnhancementMeta · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)12 citationsDec 6, 2025Training and Inference Efficiency of Encoder-Decoder Speech ModelsNVIDIA · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)10 citationsDec 6, 2025Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMsMeta · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)10 citationsDec 6, 2025mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text TasksGoogle DeepMind · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)9 citationsDec 6, 2025A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized DataNVIDIA · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)8 citationsDec 6, 2025Programmable and GPU-Accelerated Edge Inference for Real-Time ISAC on NVIDIA Aerial TestbedNVIDIA · arXiv (Cornell University)8 citationsDec 6, 2025Selection of Layers from Self-supervised Learning Models for Predicting Mean-Opinion-Score of SpeechAlphabet · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)7 citationsDec 6, 2025Towards Efficient Speech-Text Jointly Decoding within One Speech Language ModelMicrosoft · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)5 citationsDec 6, 2025CASPER: A Large Scale Spontaneous Speech DatasetMeta · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)5 citationsDec 6, 2025HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality AssessmentNVIDIA · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)4 citationsDec 6, 2025SLM-S2ST: A multimodal language model for direct speech-to-speech translationMicrosoft · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)4 citationsDec 6, 2025Customizing Speech Recognition Model with Large Language Model FeedbackMicrosoft · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)3 citationsDec 6, 2025FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual AbilitiesNVIDIA · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)2 citationsDec 6, 2025URGENT-PK: Perceptually-Aligned Ranking Model Designed for Speech Enhancement CompetitionMeta · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)2 citationsDec 6, 2025Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public DataTechnology Innovation Institute · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)2 citationsDec 6, 2025Lightweight Prompt Biasing for Contextualized End-to-End ASR SystemsMicrosoft · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)2 citationsDec 6, 2025MADASR 2.0: Multi-Lingual Multi-Dialect ASR Challenge in 8 Indian LanguagesMicrosoft · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)2 citationsDec 6, 2025Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input ManipulationiFlytek · arXiv (Cornell University)2 citationsDec 6, 2025TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting TreeNVIDIA · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)1 citationDec 6, 2025WST: Weakly Supervised Transducer for Automatic Speech RecognitionMicrosoft · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)1 citationDec 6, 2025Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive DecodingAlibaba · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)1 citationDec 6, 2025Improving Streaming ASR via Differentially Private Fusion of Data from Multiple SourcesAlphabet, Google DeepMind, OpenAI · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)Dec 6, 2025Efficient Deployment of Large Speech Recognition Models on GPUNVIDIA · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)Dec 6, 2025Efficient Speech Watermarking for Speech Synthesis via Progressive Knowledge DistillationMicrosoft · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)Dec 6, 2025