Speaker Identification
61 papers with code • 4 benchmarks • 4 datasets
Benchmarks
These leaderboards are used to track progress in Speaker Identification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
VoxCeleb1
CSI
EVI
FSC-P2
Most implemented papers
Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing
Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer.
Generative Pre-Training for Speech with Autoregressive Predictive Coding
iamyuanchung/Autoregressive-Predictive-Coding
•
•
Learning meaningful and general representations from unannotated speech that are applicable to a wide range of tasks remains challenging.
Speech2Phone: A Novel and Efficient Method for Training Speaker Recognition Models
We compare the three best architectures trained using our method to select the best one, which is the one with a shallow architecture.
Contrastive Learning of General-Purpose Audio Representations
google-research/google-research
•
•
We introduce COLA, a self-supervised pre-training approach for learning a general-purpose representation of audio.
FoolHD: Fooling speaker identification by Highly imperceptible adversarial Disturbances
fsept11/FoolHD
•
•
Speaker identification models are vulnerable to carefully designed adversarial perturbations of their input signals that induce misclassification.
Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
facebookresearch/speech-resynthesis
•
•
We propose using self-supervised discrete representations for the task of speech resynthesis.
SSAST: Self-Supervised Audio Spectrogram Transformer
YuanGongND/ssast
•
•
However, pure Transformer models tend to require more training data compared to CNNs, and the success of the AST relies on supervised pretraining that requires a large amount of labeled data and a complex training pipeline, thus limiting the practical usage of AST.
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit
PaddlePaddle/PaddleSpeech
•
•
NAACL (ACL) 2022
PaddleSpeech is an open-source all-in-one speech toolkit.
A Generative Product-of-Filters Model of Audio
We propose the product-of-filters (PoF) model, a generative model that decomposes audio spectra as sparse linear combinations of "filters" in the log-spectral domain.
A domain-agnostic approach for opinion prediction on speech
We explore a domain-agnostic approach for analyzing speech with the goal of opinion prediction.
