{"total":72,"rows":[{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129,"area":null},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"area":null},{"id":"2303.06365","title":"Explainable AI for Time Series via Virtual Inspection Layers","created":"2023-03-11","cited_by_count":23,"area":null},{"id":"2407.09522","title":"UQE: A Query Engine for Unstructured Databases","created":"2024-06-23","cited_by_count":21,"area":null},{"id":"2509.24734","title":"A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity","created":"2025-09-29","cited_by_count":18,"area":null},{"id":"2405.00934","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","created":"2024-05-02","cited_by_count":15,"area":null},{"id":"2107.14203","title":"Did the Model Change? Efficiently Assessing Machine Learning API Shifts","created":"2021-07-29","cited_by_count":13,"area":null},{"id":"2403.13086","title":"Listenable Maps for Audio Classifiers","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2107.00439","title":"What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2408.17198","title":"Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features","created":"2024-08-30","cited_by_count":7,"area":null},{"id":"2607.07907","title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","created":"2026-07-08","cited_by_count":7,"area":"safety"},{"id":"2411.01710","title":"SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation","created":"2024-11-03","cited_by_count":6,"area":null},{"id":"2411.05841","title":"FLEXtime: Filterbank learning to explain time series","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2107.04616","title":"A deep convolutional neural network that is invariant to time rescaling","created":"2021-07-09","cited_by_count":5,"area":null},{"id":"2204.01235","title":"An Analysis of Semantically-Aligned Speech-Text Embeddings","created":"2022-04-04","cited_by_count":5,"area":null},{"id":"2210.09904","title":"MaSS: Multi-attribute Selective Suppression","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2310.16318","title":"Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2505.00059","title":"BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2601.18525","title":"Closing the Modality Gap Aligns Group-Wise Semantics","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2406.13584","title":"FreqRISE: Explaining time series using frequency masking","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2407.13841","title":"Many Perception Tasks are Highly Redundant Functions of their Input Data","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2408.13648","title":"Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance","created":"2024-08-24","cited_by_count":4,"area":null},{"id":"2410.07436","title":"Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2411.08013","title":"Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech","created":"2024-11-12","cited_by_count":4,"area":null},{"id":"2111.00379","title":"EfficientWord-Net: An Open Source Hotword Detection Engine based on One-shot Learning","created":"2021-10-31","cited_by_count":3,"area":null},{"id":"2405.17615","title":"Listenable Maps for Zero-Shot Audio Classifiers","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2409.01354","title":"Explanation Space: A New Perspective into Time Series Interpretability","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2410.01482","title":"One Wave To Explain Them All: A Unifying Perspective On Feature Attribution","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2111.10235","title":"Interpreting deep urban sound classification using Layer-wise Relevance Propagation","created":"2021-11-19","cited_by_count":2,"area":null},{"id":"2202.07829","title":"Spatial Transformer K-Means","created":"2022-02-16","cited_by_count":2,"area":null},{"id":"2411.10503","title":"Everything is a Video: Unifying Modalities through Next-Frame Prediction","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2411.14642","title":"VQalAttent: a Transparent Speech Generation Pipeline based on Transformer-learned VQ-VAE Latent Space","created":"2024-11-22","cited_by_count":2,"area":null},{"id":"2505.13100","title":"Time series saliency maps: explaining models across multiple domains","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2506.13268","title":"Energy-Efficient Digital Design: A Comparative Study of Event-Driven and Clock-Driven Spiking Neurons","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2506.14775","title":"See What I Mean? CUE: A Cognitive Model of Understanding Explanations","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2507.22208","title":"Quantum-Inspired Audio Unlearning: Towards Privacy-Preserving Voice Biometrics","created":"2025-07-29","cited_by_count":2,"area":"safety"},{"id":"2303.07643","title":"Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification","created":"2023-03-14","cited_by_count":1,"area":"distill"},{"id":"2308.08125","title":"Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2505.16406","title":"On the reliability of feature attribution methods for speech classification","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2507.12979","title":"A Distributed Generative AI Approach for Heterogeneous Multi-Domain Environments under Data Sharing constraints","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2507.15523","title":"An Investigation of Test-time Adaptation for Audio Classification under Background Noise","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2509.18010","title":"Cross-Attention is Half Explanation in Speech-to-Text Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2510.19368","title":"AMAuT: A Flexible and Efficient Multiview Audio Transformer Framework Trained from Scratch","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2605.19325","title":"An Exterior Method for Nonnegative Matrix Factorization","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2205.02670","title":"Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2207.04027","title":"A Multi-tasking Model of Speaker-Keyword Classification for Keeping Human in the Loop of Drone-assisted Inspection","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2304.03969","title":"Pump It Up: Predict Water Pump Status using Attentive Tabular Learning","created":"2023-04-08","cited_by_count":0,"area":null},{"id":"2308.13722","title":"Time-to-Pattern: Information-Theoretic Unsupervised Learning for Scalable Time Series Summarization","created":"2023-08-26","cited_by_count":0,"area":null},{"id":"2309.11462","title":"AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognition","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2407.00531","title":"Interpreting Pretrained Speech Models for Automatic Speech Assessment of Voice Disorders","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2408.13696","title":"Revisiting DNN Training for Intermittently-Powered Energy-Harvesting Micro-Computers","created":"2024-08-25","cited_by_count":0,"area":null},{"id":"2409.12112","title":"Pareto Data Framework: Steps Towards Resource-Efficient Decision Making Using Minimum Viable Data (MVD)","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2504.03497","title":"Hybrid Real- and Complex-valued Neural Network Architecture","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2505.09091","title":"DPN-GAN: Inducing Periodic Activations in Generative Adversarial Networks for High-Fidelity Audio Synthesis","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2507.14579","title":"Exploring Human-AI Complementarity in CPS Diagnosis Using Unimodal and Multimodal BERT Models","created":"2025-07-19","cited_by_count":0,"area":null},{"id":"2507.17368","title":"ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2507.21483","title":"NCCR: to Evaluate the Robustness of Neural Networks and Adversarial Examples","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2511.11691","title":"Beyond saliency: enhancing explanation of speech emotion recognition with expert-referenced acoustic cues","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2511.18421","title":"DHAuDS: A Dynamic and Heterogeneous Audio Benchmark for Test-Time Adaptation","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.01537","title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2512.12086","title":"CLOAK: Contrastive Guidance for Latent Diffusion-Based Data Obfuscation","created":"2025-12-12","cited_by_count":0,"area":"diffusion"},{"id":"2602.13556","title":"Discrete-Space Generative AI Pipeline for Semantic Transmission of Signals","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.17623","title":"ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.24283","title":"Bridging Biological Hearing and Neuromorphic Computing: End-to-End Time-Domain Audio Signal Processing with Reservoir Computing","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.00207","title":"Lead Zirconate Titanate Reservoir Computing for Classification of Written and Spoken Digits","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.12168","title":"On What We Can Learn from Low-Resolution Data","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.16905","title":"AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.20675","title":"VQ4SNN: Vector Quantization for Memory-Efficient FPGA Spiking Neural Networks","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.01729","title":"DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning","created":"2026-07-02","cited_by_count":0,"area":"safety"},{"id":"2608.10857","title":"FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.29270","title":"Learnable Time-Frequency Masks for Explaining Time-Series Classifiers","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.36263","title":"Paired Multimodal Scaling Laws","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}