mlsanityData to 7 Oct 2026

TristouNet: Triplet Loss for Speaker Turn Embedding

arXiv 1609.04301 ↗First posted 14 Sep 2016cs.SD stat.MLcited by 18

Not on the map. Why?

Abstract (arXiv)

TristouNet is a neural network architecture based on Long Short-Term Memory recurrent networks, meant to project speech sequences into a fixed-dimensional euclidean space. Thanks to the triplet loss paradigm used for training, the resulting sequence embeddings can be compared directly with the euclidean distance, for speaker comparison purposes. Experiments on short (between 500ms and 5s) speech turn comparison and speaker change detection show that TristouNet brings significant improvements over the current state-of-the-art techniques for both tasks.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 3; 2023: 2; 2024: 2.

18 papers.

Sort:

  1. 2023Time Series Contrastive Learning with Information-Aware Augmentationscited by 52
  2. 2021End-to-End Speech Recognition from Federated Acoustic Modelscited by 30
  3. 2021Learning Efficient Representations for Keyword Spotting with Triplet Losscited by 24
  4. 2021Token-Level Supervised Contrastive Learning for Punctuation Restorationcited by 14
  5. 2021Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognitioncited by 10
  6. 2022Auxiliary Cross-Modal Representation Learning with Triplet Loss Functions for Online Handwriting Recognitioncited by 6
  7. 2022The effect of speech pathology on automatic speaker verification -- a large-scale studycited by 5
  8. 2021Driver2vec: Driver Identification from Automotive Datacited by 3
  9. 2021Real Additive Margin Softmax for Speaker Verificationcited by 3
  10. 2021Speaker attribution with voice profiles by graph-based semi-supervised learningcited by 2
  11. 2024GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-shot Keyword Spottingcited by 2
  12. 2021Adaptive Margin Circle Loss for Speaker Verificationcited by 1
6 more
  1. 2022Supervised Training of Siamese Spiking Neural Networks with Earth Mover's Distancecited by 1
  2. 2021Triplet loss based embeddings for forensic speaker identification in Spanishcited by 0
  3. 2021Deep Metric Learning Model for Imbalanced Fault Diagnosiscited by 0
  4. 2021Improving Prediction of Cognitive Performance using Deep Neural Networks in Sparse Datacited by 0
  5. 2023Multi-microphone Automatic Speech Segmentation in Meetings Based on Circular Harmonics Featurescited by 0
  6. 2024Selection of Prompt Engineering Techniques for Code Generation through Predicting Code Complexitycited by 0