An End-to-end Text-independent Speaker Verification Framework With A Keyword Adversarial Network

Abstract

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 an embedding vector which distinguishes the speaker characteristics of the input utterance, while the ASR network learns to recognize the phonetic context of the input. In training our speaker verification framework, we consider both the triplet loss minimization and adversarial gradient of the ASR network to obtain more discriminative and text-independent speaker embedding vectors. With the triplet loss, the distances between the embedding vectors of the same speaker are minimized while those of different speakers are maximized. Also, with the adversarial gradient of the ASR network, the text-dependency of the speaker embedding vector can be reduced. In the experiments, we evaluated our speaker verification framework using the LibriSpeech and CHiME 2013 dataset, and th

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyyun2019an

Related papers

• Adapting End-to-end Neural Speaker Verification To New Languages And Recording Conditions With Adversarial Training (2018)9.59
• SEEF-ALDR: A Speaker Embedding Enhancement Framework Via Adversarial Learning Based Disentangled Representation (2019)3.58
• Speaker Verification Using End-to-end Adversarial Language Adaptation (2018)11.19
• Generative Adversarial Speaker Embedding Networks For Domain Robust End-to-end Speaker Verification (2018)0.00
• A Joint Noise Disentanglement And Adversarial Training Framework For Robust Speaker Verification (2024)6.34
• End-to-end Attention Based Text-dependent Speaker Verification (2017)14.87
• DEAAN: Disentangled Embedding And Adversarial Adaptation Network For Robust Speaker Representation Learning (2020)9.59
• Triplet Based Embedding Distance And Similarity Learning For Text-independent Speaker Verification (2019)5.24