mlsanityData to 14 Oct 2026

Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System

arXiv 1804.05160 ↗First posted 14 Apr 2018eess.AS cs.LG cs.SDcited by 47

Not on the map. Why?

Abstract (arXiv)

In this paper, we explore the encoding/pooling layer and loss function in the end-to-end speaker and language recognition system. First, a unified and interpretable end-to-end system for both speaker and language recognition is developed. It accepts variable-length input and produces an utterance level result. In the end-to-end system, the encoding layer plays a role in aggregating the variable-length input sequence into an utterance level representation. Besides the basic temporal average pooling, we introduce a self-attentive pooling layer and a learnable dictionary encoding layer to get the utterance level representation. In terms of loss function for open-set speaker verification, to get more discriminative speaker embedding, center loss and angular softmax loss is introduced in the end-to-end system. Experimental results on Voxceleb and NIST LRE 07 datasets show that the performance of end-to-end learning system could be significantly improved by the proposed encoding layer and loss function.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 11; 2023: 11; 2024: 6; 2025: 4; 2026: 4.

47 papers.

Sort:

By area:

  1. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  2. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 278
  3. 2021Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularizationcited by 17
  4. 2023On the Robustness of Arabic Speech Dialect Identificationcited by 13
  5. 2022Deepfake audio detection by speaker verificationcited by 11
  6. 2022Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learningcited by 10
  7. 2021Multi-task Voice Activated Framework using Self-supervised Learningcited by 9
  8. 2021Multi-View Self-Attention Based Transformer for Speaker Recognitioncited by 8
  9. 2023Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillationcited by 6
  10. 2024USAT: A Universal Speaker-Adaptive Text-to-Speech Approachcited by 6
  11. 2021SIG-VC: A Speaker Information Guided Zero-shot Voice Conversion System for Both Human Beings and Machinescited by 5
  12. 2022Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learningcited by 5
35 more
  1. 2022A Compact End-to-End Model with Local and Global Context for Spoken Language Identificationcited by 5
  2. 2022Large-scale learning of generalised representations for speaker recognitioncited by 4
  3. 2025Synthetic Speech Source Tracing using Metric Learningcited by 4
  4. 2021Real Additive Margin Softmax for Speaker Verificationcited by 3
  5. 2023Improving Transformer-based Networks With Locality For Automatic Speaker Verificationcited by 3
  6. 2023Towards spoken dialect identification of Irishcited by 3
  7. 2024Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesiscited by 3
  8. 2026Explainable AI in Speaker Recognition -- Making Latent Representations Understandablecited by 3
  9. 2021Binary Neural Network for Speaker Verificationcited by 2
  10. 2022Pretraining Approaches for Spoken Language Recognition: TalTech Submission to the OLR 2021 Challengecited by 2
  11. 2023A Study on Bias and Fairness In Deep Speaker Recognitioncited by 2
  12. 2023VIFS: An End-to-End Variational Inference for Foley Sound Synthesiscited by 2
  13. 2023RADIO: Reference-Agnostic Dubbing Video Synthesiscited by 2
  14. 2024Enhancing Risk Assessment in Transformers with Loss-at-Risk Functionscited by 2
  15. 2025DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Predictioncited by 2
  16. 2026Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluationcited by 2
  17. 2021Adaptive Margin Circle Loss for Speaker Verificationcited by 1
  18. 2021GC-TTS: Few-shot Speaker Adaptation with Geometric Constraintscited by 1
  19. 2022Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognitioncited by 1
  20. 2022Neural Inference of Gaussian Processes for Time Series Data of Quasarscited by 1
  21. 2024Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learningcited by 1
  22. 2024Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examplescited by 1
  23. 2025Auditory Intelligence: Understanding the World Through Soundcited by 1
  24. 2026Beyond Short Segments : Expanding Speaker Embeddings with Vector Archivescited by 1
  25. 2021Low-Resource Spoken Language Identification Using Self-Attentive Pooling and Deep 1D Time-Channel Separable Convolutionscited by 0
  26. 2021A Study of Multimodal Person Verification Using Audio-Visual-Thermal Datacited by 0
  27. 2022Towards a Common Speech Analysis Enginecited by 0
  28. 2022Generation of Speaker Representations Using Heterogeneous Training Batch Assemblycited by 0
  29. 2022Bi-LSTM Scoring Based Similarity Measurement with Agglomerative Hierarchical Clustering (AHC) for Speaker Diarizationcited by 0
  30. 2023Unsupervised Speech Representation Pooling Using Vector Quantizationcited by 0
  31. 2023Progressive Sub-Graph Clustering Algorithm for Semi-Supervised Domain Adaptation Speaker Verificationcited by 0
  32. 2023Ordered and Binary Speaker Embeddingcited by 0
  33. 2024Who is Authentic Speakercited by 0
  34. 2025TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Routecited by 0
  35. 2026Self-Supervised Learning for Speaker Recognition: A study and reviewcited by 0