Tristounet: Triplet Loss For Speaker Turn Embedding

Abstract

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.

Stats

• citations93
• S2 citations—
• github stars0
• HF likes0
• heat score14.80
• arxiv keybredin2016tristounet

Related papers

• Triplet Based Embedding Distance And Similarity Learning For Text-independent Speaker Verification (2019)5.24
• Triplet Network With Attention For Speaker Diarization (2018)7.16
• Triplet Loss Based Embeddings For Forensic Speaker Identification In Spanish (2021)2.26
• End-to-end Triplet Loss Based Emotion Embedding System For Speech Emotion Recognition (2020)10.35
• Triplet Entropy Loss: Improving The Generalisation Of Short Speech Language Identification Systems (2020)0.00
• Learning Efficient Representations For Keyword Spotting With Triplet Loss (2021)11.76
• Latent Space Representation For Multi-target Speaker Detection And Identification With A Sparse Dataset Using Triplet Neural Networks (2019)5.24
• Learning Acoustic Word Embeddings With Phonetically Associated Triplet Network (2018)0.00