End-to-End Attention based Text-Dependent Speaker Verification
A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown promising results. The extracted frame-level (DNN bottleneck, posterior or d-vector) features are equally weighted and aggregated to compute an utterance-level speaker representation (d-vector or i-vector). In this work we use speaker discriminative CNNs to extract the noise-robust frame-level features. These features are smartly combined to form an utterance-level speaker vector through an attention mechanism. The proposed attention model takes the speaker discriminative information and the phonetic information to learn the weights. The whole system, including the CNN and attention model, is joint optimized using an end-to-end criterion. The training algorithm imitates exactly the evaluation process --- directly mapping a test utterance and a few target speaker utterances into a single verification score. The algorithm can automatically select the most similar impostor for each target speaker to train the network. We demonstrated the effectiveness of the proposed end-to-end system on Windows $10$ "Hey Cortana" speaker verification task.
Code (0)
등록된 구현이 없습니다.
Tasks
Speaker VerificationText-Dependent Speaker VerificationSimilar Papers 제목 키워드 기반
Attention Back-end for Automatic Speaker Verification with Multiple Enrollment Utterances
Probabilistic linear discriminant analysis (PLDA) or cosine similarity have been widely used in traditional speaker verification systems as back-end techniques to measure pairwise similarities. To make better use of mult…
Speaker VerificationAttention-Based Models for Text-Dependent Speaker Verification
Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands …
Image CaptioningMachine TranslationSpeaker RecognitionSpeaker Verification+4MFA: TDNN with Multi-scale Frequency-channel Attention for Text-independent Speaker Verification with Short Utterances
The time delay neural network (TDNN) represents one of the state-of-the-art of neural solutions to text-independent speaker verification. However, they require a large number of filters to capture the speaker characteris…
Speaker VerificationText-Independent Speaker VerificationAn Empirical Study on Text-Independent Speaker Verification based on the GE2E Method
While many researchers in the speaker recognition area have started to replace the former classical state-of-the-art methods with deep learning techniques, some of the traditional i-vector-based methods are still state-o…
Speaker RecognitionSpeaker VerificationText-Independent Speaker VerificationText-dependent Speaker Verification (TdSV) Challenge 2024: Challenge Evaluation Plan
This document outlines the Text-dependent Speaker Verification (TdSV) Challenge 2024, which centers on analyzing and exploring novel approaches for text-dependent speaker verification. The primary goal of this challenge …
Few-Shot LearningMulti-Task LearningSelf-Supervised LearningSpeaker Verification+1