Generalized End-to-end Loss For Speaker Verification

Abstract

In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function. Unlike TE2E, the GE2E loss function updates the network in a way that emphasizes examples that are difficult to verify at each step of the training process. Additionally, the GE2E loss does not require an initial stage of example selection. With these properties, our model with the new loss function decreases speaker verification EER by more than 10%, while reducing the training time by 60% at the same time. We also introduce the MultiReader technique, which allows us to do domain adaptation - training a more accurate model that supports multiple keywords (i.e. "OK Google" and "Hey Google") as well as multiple dialects.

Stats

• citations553
• S2 citations—
• github stars0
• HF likes0
• heat score20.58
• arxiv keywan2017generalized

Related papers

• An Empirical Study On Text-independent Speaker Verification Based On The GE2E Method (2020)0.00
• End-to-end Trainable Self-attentive Shallow Network For Text-independent Speaker Verification (2020)0.00
• End-to-end Residual CNN With L-GM Loss Speaker Verification System (2018)2.26
• Joint Speaker Encoder And Neural Back-end Model For Fully End-to-end Automatic Speaker Verification With Multiple Enrollment Utterances (2022)0.00
• Angular Softmax Loss For End-to-end Speaker Verification (2018)11.19
• End-to-end Losses Based On Speaker Basis Vectors And All-speaker Hard Negative Mining For Speaker Verification (2019)0.00
• Feature Enhancement With Deep Feature Losses For Speaker Verification (2019)10.61
• Voiceid Loss: Speech Enhancement For Speaker Verification (2019)13.39