Data to 14 Oct 2026

Deep Speaker: an End-to-End Neural Speaker Embedding System

arXiv 1705.02304 ↗First posted 5 May 2017cs.CLcited by 58

Not on the map. Why?

Abstract (arXiv)

We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including speaker identification, verification, and clustering. We experiment with ResCNN and GRU architectures to extract the acoustic features, then mean pool to produce utterance-level speaker embeddings, and train using triplet loss based on cosine similarity. Experiments on three distinct datasets suggest that Deep Speaker outperforms a DNN-based i-vector baseline. For example, Deep Speaker reduces the verification equal error rate by 50% (relatively) and improves the identification accuracy by 60% (relatively) on a text-independent dataset. We also present results that suggest adapting from a model trained with Mandarin can improve accuracy for English speaker recognition.

Key facts. Cited by 58 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 15; 2023: 11; 2024: 7; 2025: 3; 2026: 3.

58 papers.

Sort:

By area:

2021AdaSpeech: Adaptive Text to Speech for Custom Voicecited by 98
2021Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detectioncited by 32
2021Learning Efficient Representations for Keyword Spotting with Triplet Losscited by 24
2022Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognitioncited by 23
2022Bias in Automated Speaker Recognitioncited by 20
2021STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speechcited by 18
2022Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chesscited by 18
2021AdaSpeech 2: Adaptive Text to Speech with Untranscribed Datacited by 17
2024DiarizationLM: Speaker Diarization Post-Processing with Large Language Modelscited by 16
2023Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correctioncited by 14
2024CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Modelscited by 13
2022MFA: TDNN with Multi-scale Frequency-channel Attention for Text-independent Speaker Verification with Short Utterancescited by 12

38 more

2021Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognitioncited by 10
2022AS2T: Arbitrary Source-To-Target Adversarial Attack on Speaker Recognition Systemscited by 10
2021A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter Itcited by 8
2022Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentificationcited by 8
2023ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptationcited by 7
2022ECAPA-TDNN for Multi-speaker Text-to-speech Synthesiscited by 5
2023Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understandingcited by 5
2022HEFT: Homomorphically Encrypted Fusion of Biometric Templatescited by 4
2023Catch You and I Can: Revealing Source Voiceprint Against Voice Conversioncited by 4
2023Label Aware Speech Representation Learning For Language Identificationcited by 4
2025Voice Cloning: Comprehensive Surveycited by 4
2021Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognitioncited by 3
2021SEC4SR: A Security Analysis Platform for Speaker Recognitioncited by 3
2021Real Additive Margin Softmax for Speaker Verificationcited by 3
2022Robust Vocal Quality Feature Embeddings for Dysphonic Voice Detectioncited by 3
2023CryCeleb: A Speaker Verification Dataset Based on Infant Cry Soundscited by 3
2023Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizercited by 3
2021Speaker attribution with voice profiles by graph-based semi-supervised learningcited by 2
2021SVEva Fair: A Framework for Evaluating Fairness in Speaker Verificationcited by 2
2021Optimized Power Normalized Cepstral Coefficients towards Robust Deep Speaker Verificationcited by 2
2022Transducer-based language embedding for spoken language identificationcited by 2
2022Automatic Evaluation of Speaker Similaritycited by 2
2022Defend Data Poisoning Attacks on Voice Authenticationcited by 2
2023SVVAD: Personal Voice Activity Detection for Speaker Verificationcited by 2
2023Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakerscited by 2
2024Securing Voice Authentication Applications Against Targeted Data Poisoningcited by 2
2025A Survey of Threats Against Voice Authentication and Anti-Spoofing Systemscited by 2
2021Adaptive Margin Circle Loss for Speaker Verificationcited by 1
2021GC-TTS: Few-shot Speaker Adaptation with Geometric Constraintscited by 1
2022AutoLV: Automatic Lecture Video Generatorcited by 1
2022Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognitioncited by 1
2023Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTScited by 1
2025Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systemscited by 1
2021Triplet loss based embeddings for forensic speaker identification in Spanishcited by 0
2021Confidence Calibration with Bounded Error Using Transformationscited by 0
2021Blind Speech Separation and Dereverberation using Neural Beamformingcited by 0
2021Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influencecited by 0
2022Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neuronscited by 0

50 most cited of 58 All 58 (JSON)