Asymmetric Correspondence Learning for Lexical and Style Embeddings: Interpreting Latent Space via Acoustic Features
cs.CL, cs.SD
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Self-Supervised Acoustic Word Embedding Learning via Correspondence Transformer Encoder
- Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings
- Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches
- Deep convolutional acoustic word embeddings using word-pair side information
- Evaluating the reliability of acoustic speech embeddings
- Designing and Interpreting Probes with Control Tasks
- Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
- Layer Normalization
- Gaussian Error Linear Units (GELUs)
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data