REVIEW 22 cited by
VoxCeleb: a large-scale speaker identification dataset
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
VoxCeleb: a large-scale speaker identification dataset
read the original abstract
Most existing datasets for speaker identification contain samples obtained under quite constrained conditions, and are usually hand-annotated, hence limited in size. The goal of this paper is to generate a large scale text-independent speaker identification dataset collected 'in the wild'. We make two contributions. First, we propose a fully automated pipeline based on computer vision techniques to create the dataset from open-source media. Our pipeline involves obtaining videos from YouTube; performing active speaker verification using a two-stream synchronization Convolutional Neural Network (CNN), and confirming the identity of the speaker using CNN based facial recognition. We use this pipeline to curate VoxCeleb which contains hundreds of thousands of 'real world' utterances for over 1,000 celebrities. Our second contribution is to apply and compare various state of the art speaker identification techniques on our dataset to establish baseline performance. We show that a CNN based architecture obtains the best performance for both identification and verification.
Forward citations
Cited by 22 Pith papers
-
Beyond Universality: The GCC-FER Dataset and Culture-Aware Adaptation for Dynamic Facial Expression Recognition
A new multicultural DFER dataset GCC-FER is presented along with a culture-aware adaptation method that improves recognition performance on GCC-FER and DFEW.
-
Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues
ToxiAlert-Bench dataset and dual-head neural network detect toxic speech by distinguishing textual versus paralinguistic sources, reporting 21.1% Macro-F1 and 13% accuracy gains over baselines.
-
V.O.I.C.E (Voice, Ownership, Identity, Control, Expression): Risk Taxonomy of Synthetic Voice Generation From Empirical Data
V.O.I.C.E is a new taxonomy that organizes synthetic voice risks into five categories and shows how they interact with exposure, visibility, and legal context using empirical incident data.
-
ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection
ICLAD combines in-context learning and comparison guidance in audio language models with a routing detector to boost generalization and explanations for audio deepfake detection, achieving up to 2x F1 gains on wild data.
-
The DeepSpeak Dataset
DeepSpeak provides over 100 hours of consented, identity-matched real and modern deepfake audiovisual content focused on talking heads, with evaluations showing existing detectors fail to generalize without retraining.
-
PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction
Proxy-supervised joint fine-tuning of a BSRNN separator with ASR, speaker-similarity, VAD and DNSMOS losses on a new 71k real-conversation corpus yields the best SIM and timing F1 on REAL-T.
-
ReAge3D: Re-Aging 3D Faces with View Consistency
ReAge3D trains a diffusion re-aging model on synthetic pairs then uses masked propagation from a frontal pivot view to produce consistent multi-view images that supervise 3D face optimization.
-
Explainable AI in Speaker Recognition -- Making Latent Representations Understandable
Speaker recognition networks form hierarchical clusters in latent space that can be matched to semantic classes using new HCCM algorithm and quantified by Liebig's score.
-
A Camera-Native Talking-Head Video Dataset for Various Computer Vision Tasks
A 847-clip camera-native talking-head dataset with MOS annotations and a 120-clip stratified benchmark shows content type and background processing significantly change modern codec BD-rate savings.
-
Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
Seed-TTS models produce speech matching human naturalness and speaker similarity, with added controllability via self-distillation and reinforcement learning.
-
Speaker Recognition with Random Digit Strings Using Uncertainty Normalized HMM-based i-vectors
Digit-specific HMM i-vectors with uncertainty normalization reach 1.52% male and 1.77% female EER on RSR2015 part III using only that corpus and simple cosine scoring.
-
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
A system-first taxonomy and literature synthesis of multimodal unlearning across vision, language, video, and audio, with datasets, benchmarks, metrics, applications, and open challenges.
-
Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation
The paper introduces Modified RISE-eval to evaluate GradCAM and LayerCAM attention maps on speaker recognition networks and reports distinct advantages for each method under different conditions.
-
LISE : Listenable Interpretable Speaker Embeddings
LISE decomposes pretrained speaker embeddings into components that preserve ASV performance with negligible EER degradation and enable listeners to distinguish speakers at 83.9% accuracy.
-
CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation
Introduces CineDance-1M dataset for multi-shot long-form text-to-audio-video generation along with CineBench and a model adaptation.
-
ChaRVoC: A Challenge-Response Voice Cancelable Authentication System
ChaRVoC integrates voice biometrics, user secret keys, and dynamic challenges via a HashGray-XOR scheme to produce cancelable, unlinkable, non-invertible templates with liveness detection.
-
Dual-LoRA: Parameter-Efficient Adversarial Disentanglement for Cross-Lingual Speaker Verification
Dual-LoRA with a language-anchored adversary achieves 0.91% EER on the TidyVoice benchmark for cross-lingual speaker verification by targeting true linguistic cues while preserving speaker discriminability.
-
ULTRAS -- Unified Learning of Transformer Representations for Audio and Speech Signals
ULTRAS unifies audio and speech representation learning in a single transformer by applying patch masking to log-mel spectrograms and using a joint spectral-temporal prediction loss.
-
Towards Robust Uncertainty-Aware Speaker Modeling
Inter- and intra-speaker hardness in an uncertainty-aware softmax plus source-prior uncertainty calibration improves speaker verification reliability under domain shift.
-
Neural Speaker Diarization via Multilingual Training: Evaluation on Low-Resource Nepali-Hindi Speech
Multilingual training of EEND-EDA and DiaPer models produces low diarization error rates on Nepali-Hindi speech, with DiaPer outperforming EEND-EDA in multi-speaker conditions.
-
Explainable AI in Speaker Recognition -- Making Latent Representations Understandable
Hierarchical clustering of speaker recognition embeddings reveals that the network organizes representations by gender at upper levels and by gender-nationality conjunctions at lower levels, interpreted via a proposed...
-
Dementia classification from spontaneous speech using wrapper-based feature selection
Using full-recording acoustic features and wrapper selection, the Extreme Minimal Learning Machine provides competitive dementia classification accuracy at lower computational cost on ADReSS and Pitt datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.