Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
ZSVC: Zero-shot Style Voice Conversion with Disentangled Latent Diffusion Models and Adversarial TrainingMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing4 citationsMar 12, 2025Learning Rate Annealing Improves Tuning Robustness in Stochastic OptimizationAlphabet · arXiv (Cornell University)3 citationsMar 12, 2025SciFi-Benchmark: Leveraging Science Fiction To Improve Robot BehaviorAlphabet, Google DeepMind · arXiv (Cornell University)3 citationsMar 12, 2025Foundation Model and Temporal Priors-guided Transductive Few-shot Action RecognitionAllen Institute for AI · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025Speech Few-Shot Learning for Language Learners’ Speech RecognitionAlphabet · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025FashionFAE: Fine-grained Attributes Enhanced Fashion Vision-Language Pre-trainingAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing TasksNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through CamouflageAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025TTS-Transducer: End-to-End Speech Synthesis with Neural TransducerNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025Full-Reference Point Cloud Quality Assessment with Multimodal Large Language ModelsAlphabet · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025InstantSpeech: Instant Synchronous Text-to-Speech Synthesis for LLM-driven Voice ChatbotsNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025Span Attention for Entity-Consistent Task-Oriented Dialogue Response GenerationAlphabet · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025Scaling Bioacoustic Signal Pre-training with Million Samples Via Mask-ModelingiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing3 citationsMar 12, 2025Resilient Test-Time Adaptation by Mitigating Batch-Normalization OverfittingNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025A Small-footprint Acoustic Echo Cancellation Solution for Mobile Full-Duplex Speech InteractionsAlibaba · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025CorrGAN: Simultaneous Learning of Speech Enhancement and Perceptual Quality Loss FunctionsMicrosoft · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025Transcribing and Translating, Fast and Slow: Joint Speech Translation and RecognitionMeta · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025Perceptual Audio Coding: A 40-Year Historical PerspectiveAlphabet · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025Identifying and Mitigating Mismatched Language Code in Multilingual ASRAlphabet · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASRMeta · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025Advancing Active Speaker Detection for Egocentric VideosMeta · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASRNVIDIA · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025Tool Playgrounds: A Comprehensive and Analyzable Benchmark for LLM Tool InvocationSenseTime · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025Anchored Monotonic Alignment and Representation Substitution for Rare Spontaneous Behaviors in Spontaneous Speech SynthesisiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025pFedFace: Personalized Federated Learning for Face RecognitionMininglamp Technology · IEEE International Conference on Acoustics Speech and Signal Processing2 citationsMar 12, 2025