Triplet Loss Based Embeddings For Forensic Speaker Identification In Spanish
2021 · Emmanuel Maqueda, Javier Alvarez-Jimenez, Carlos Mena, et al.
Abstract
With the advent of digital technology, it is more common that committed crimes or legal disputes involve some form of speech recording where the identity of a speaker is questioned [1]. In face of this situation, the field of forensic speaker identification has been looking to shed light on the problem by quantifying how much a speech recording belongs to a particular person in relation to a population. In this work, we explore the use of speech embeddings obtained by training a CNN using the triplet loss. In particular, we focus on the Spanish language which has not been extensively studies. We propose extracting the embeddings from speech spectrograms samples, then explore several configurations of such spectrograms, and finally, quantify the embeddings quality. We also show some limitations of our data setting which is predominantly composed by male speakers. At the end, we propose two approaches to calculate the Likelihood Radio given out speech embeddings and we show that triplet
Authors
(none)
Tags
Stats
Related papers
- Triplet Entropy Loss: Improving The Generalisation Of Short Speech Language Identification Systems (2020)0.00
- Triplet Based Embedding Distance And Similarity Learning For Text-independent Speaker Verification (2019)5.24
- 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
- Tristounet: Triplet Loss For Speaker Turn Embedding (2016)14.80
- Scenario Aware Speech Recognition: Advancements For Apollo Fearless Steps & Chime-4 Corpora (2021)5.84
- An Enhanced Conv-tasnet Model For Speech Separation Using A Speaker Distance-based Loss Function (2022)0.00
- End-to-end Triplet Loss Based Emotion Embedding System For Speech Emotion Recognition (2020)10.35