Speaker Verification

Speaker verification is the verifying the identity of a person from characteristics of the voice.

( Image credit: Contrastive-Predictive-Coding-PyTorch )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 401–425 of 746 papers

Title	Date	Tasks	Status	Hype
Improving Text-Independent Speaker Verification with Auxiliary Speakers Using Graph	Sep 20, 2021	Speaker VerificationText-Independent Speaker Verification	—Unverified	0
SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification	Sep 18, 2021	Neural Architecture SearchSpeaker Recognition	CodeCode Available	1
Studying squeeze-and-excitation used in CNN for speaker verification	Sep 13, 2021	Speaker Verification	—Unverified	0
The IDLAB VoxCeleb Speaker Recognition Challenge 2021 System Description	Sep 9, 2021	Speaker RecognitionSpeaker Verification	—Unverified	0
The DKU-DukeECE System for the Self-Supervision Speaker Verification Task of the 2021 VoxCeleb Speaker Recognition Challenge	Sep 7, 2021	Pseudo LabelRepresentation Learning	—Unverified	0
FastAudio: A Learnable Audio Front-End for Spoof Speech Detection	Sep 6, 2021	Speaker IdentificationSpeaker Verification	CodeCode Available	1
Efficient Attention Branch Network with Combined Loss Function for Automatic Speaker Verification Spoof Detection	Sep 5, 2021	Speaker VerificationSpoof Detection	CodeCode Available	1
The Phonexia VoxCeleb Speaker Recognition Challenge 2021 System Description	Sep 5, 2021	ClusteringContrastive Learning	—Unverified	0
CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations	Sep 1, 2021	Emotion ClassificationLanguage Modeling	CodeCode Available	1
ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan	Sep 1, 2021	Face SwappingSpeaker Verification	CodeCode Available	1
Physiological-Physical Feature Fusion for Automatic Voice Spoofing Detection	Sep 1, 2021	Speaker VerificationSpeech Synthesis	—Unverified	0
ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection	Sep 1, 2021	Face SwappingSpeaker Verification	—Unverified	0
Task-aware Warping Factors in Mask-based Speech Enhancement	Aug 27, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified	0
FDN: Finite Difference Network with Hierarchical Convolutional Features for Text-independent Speaker Verification	Aug 18, 2021	RhythmSpeaker Verification	CodeCode Available	0
RW-Resnet: A Novel Speech Anti-Spoofing Model Using Raw Waveform	Aug 12, 2021	Speaker VerificationSynthetic Speech Detection	—Unverified	0
Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing	Aug 2, 2021	Acoustic Unit DiscoveryLanguage Modeling	CodeCode Available	0
Practical Attacks on Voice Spoofing Countermeasures	Jul 30, 2021	Speaker Verification	—Unverified	0
End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection	Jul 27, 2021	Audio Deepfake DetectionDeepFake Detection	CodeCode Available	1
SVEva Fair: A Framework for Evaluating Fairness in Speaker Verification	Jul 26, 2021	FairnessSpeaker Verification	CodeCode Available	1
Use of speaker recognition approaches for learning and evaluating embedding representations of musical instrument sounds	Jul 24, 2021	Data AugmentationInstrument Recognition	CodeCode Available	0
Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks	Jul 19, 2021	Speaker Verification	CodeCode Available	1
Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding	Jul 14, 2021	Speaker VerificationText-Independent Speaker Verification	—Unverified	0
Representation Learning to Classify and Detect Adversarial Attacks against Speaker and Speech Recognition Systems	Jul 9, 2021	Representation LearningSpeaker Identification	—Unverified	0
MACCIF-TDNN: Multi aspect aggregation of channel and context interdependence features in TDNN-based speaker verification	Jul 7, 2021	Speaker Verification	—Unverified	0
Multi-user VoiceFilter-Lite via Attentive Speaker Embedding	Jul 2, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified	0

Show:10 25 50

← PrevPage 17 of 30Next →

All datasets VoxCeleb VoxCeleb1 CALLHOME CN-CELEB ASVspoof 2019 - LA VibraVox (forehead accelerometer)VibraVox (headset microphone)VibraVox (rigid in-ear microphone)VibraVox (soft in-ear microphone)VibraVox (temple vibration pickup)VibraVox (throat microphone)VoxCeleb2

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Multi Task SSL	EER	1.98	—	Unverified
2	ReDimNet-B0-LM (1.0M)	EER	1.16	—	Unverified
3	TitanNet -S	EER	1.15	—	Unverified
4	ReDimNet-B0-LM-ASNorm (1.0M)	EER	1.07	—	Unverified
5	SpeechNAS	EER	1.02	—	Unverified
6	ReDimNet-B1-LM (2.2M)	EER	0.85	—	Unverified
7	TitanNet -M	EER	0.81	—	Unverified
8	ReDimNet-B1-LM-ASNorm (2.2M)	EER	0.73	—	Unverified
9	TitanNet -L	EER	0.68	—	Unverified
10	ReDimNet-B2-SF2-LM (4.7M)	EER	0.57	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Fine-tuned HuBERT Large	EER	2.36	—	Unverified
2	ReDimNet-B0-LM (1.0M)	EER	1.16	—	Unverified
3	ReDimNet-B0-LM-ASNorm (1.0M)	EER	1.07	—	Unverified
4	SpeechNAS	EER	1.02	—	Unverified
5	ReDimNet-B1-LM (2.2M)	EER	0.85	—	Unverified
6	ReDimNet-B1-LM-ASNorm (2.2M)	EER	0.73	—	Unverified
7	ReDimNet-B2-SF2-LM (4.7M)	EER	0.57	—	Unverified
8	ReDimNet-B2-SF2-LM-ASNorm (4.7M)	EER	0.52	—	Unverified
9	ReDimNet-B4-LM (6.3M)	EER	0.51	—	Unverified
10	ReDimNet-B3-LM (3.0M)	EER	0.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GE2E	Cosine EER	3.55	—	Unverified
2		Cosine EER	2.38	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet with Attention Backend	EER	10.77	—	Unverified
2	X-Vectors with Attention Backend	EER	10.12	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ECAPA-TDNN	minDCF	0	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ECAPA2	Test EER	0.01	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ECAPA2	Test EER	0	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ECAPA2	Test EER	0.03	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ECAPA2	Test EER	0.02	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ECAPA2	Test EER	0.08	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ECAPA2	Test EER	0.04	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet-50	EER	100	—	Unverified