FineSpeaker: Reliable Speaker Representation Learning at Fine Temporal Resolution
cs.SD
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
- CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking
- Deep Speaker: an End-to-End Neural Speaker Embedding System
- An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification
- ERes2NetV2: Boosting Short-Duration Speaker Verification Performance with Computational Efficiency
- Reshape Dimensions Network for Speaker Recognition
- ReDimNet2: Scaling Speaker Verification via Time-Pooled Dimension Reshaping
- Whisper-PMFA: Partial Multi-Scale Feature Aggregation for Speaker Verification using Whisper Models
- Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances
- Auto-Encoding Variational Bayes
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
- Flow Matching for Generative Modeling
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
- DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection
- An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- Longformer: The Long-Document Transformer
- VoxCeleb2: Deep Speaker Recognition
- Spot the conversation: speaker diarisation in the wild
- AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems