paper-with-me

Papers

Triplet Based Embedding Distance and Similarity Learning for Text-independent Speaker Verification

2019-08-06 · Zongze Ren, Zhiyong Chen, Shugong Xu

Speaker embeddings become growing popular in the text-independent speaker verification task. In this paper, we propose two improvements during the training stage. The improvements are both based on triplet cause the training stage and the evaluation stage of the baseline x-vector system focus on different aims. Firstly, we introduce triplet loss for optimizing the Euclidean distances between embeddings while minimizing the multi-class cross entropy loss. Secondly, we design an embedding similarity measurement network for controlling the similarity between the two selected embeddings. We further jointly train the two new methods with the original network and achieve state-of-the-art. The multi-task training synergies are shown with a 9% reduction equal error rate (EER) and detected cost function (DCF) on the 2016 NIST Speaker Recognition Evaluation (SRE) Test Set.

📄 PDF Abstract BibTeX arXiv:1908.02283

Code (0)

등록된 구현이 없습니다.

Tasks

Speaker RecognitionSpeaker VerificationText-Independent Speaker VerificationTriplet

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Similar Papers 제목 키워드 기반

Convolutional Embedding for Edit Distance

2020-01-31 · Xinyan Dai, Xiao Yan, Kaiwen Zhou, Yuxuan Wang 외

Edit-distance-based string similarity search has many applications such as spell correction, data de-duplication, and sequence alignment. However, computing edit distance is known to have high complexity, which makes str…

Triplet

Jointly Learning Multiple Measures of Similarities from Triplet Comparisons

2015-03-05 · Liwen Zhang, Subhransu Maji, Ryota Tomioka

Similarity between objects is multi-faceted and it can be easier for human annotators to measure it when the focus is on a specific aspect. We consider the problem of mapping objects into view-specific embeddings where t…

Metric LearningTriplet

An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network

2019-08-06 · Sungrack Yun, Janghoon Cho, Jungyun Eum, Wonil Chang 외

This paper presents an end-to-end text-independent speaker verification framework by jointly considering the speaker embedding (SE) network and automatic speech recognition (ASR) network. The SE network learns to output …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Speaker Verificationspeech-recognition+3

StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples

2024-10-16 · Ajay Patel, Jiacheng Zhu, Justin Qiu, Zachary Horvitz 외

Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content. However, the contrastive triplets often used for training these representatio…

Contrastive LearningLanguage ModelingLanguage ModellingLarge Language Model

Active Ordinal Querying for Tuplewise Similarity Learning

2019-10-09 · Gregory Canal, Stefano Fenu, Christopher Rozell

Many machine learning tasks such as clustering, classification, and dataset search benefit from embedding data points in a space where distances reflect notions of relative similarity as perceived by humans. A common way…

ClusteringTriplet