Deep Discriminative Feature Learning for Accent Recognition

Abstract

Accent recognition with deep learning framework is a similar work to deep speaker identification, they're both expected to give the input speech an identifiable representation. Compared with the individual-level features learned by speaker identification network, the deep accent recognition work throws a more challenging point that forging group-level accent features for speakers. In this paper, we borrow and improve the deep speaker identification framework to recognize accents, in detail, we adopt Convolutional Recurrent Neural Network as front-end encoder and integrate local features using Recurrent Neural Network to make an utterance-level accent representation. Novelly, to address overfitting, we simply add Connectionist Temporal Classification based speech recognition auxiliary task during training, and for ambiguous accent discrimination, we introduce some powerful discriminative loss functions in face recognition works to enhance the discriminative power of accent features. We show that our proposed network with discriminative training method (without data-augment) is significantly ahead of the baseline system on the accent classification track in the Accented English Speech Recognition Challenge 2020, where the loss function Circle-Loss has achieved the best discriminative optimization for accent representation.

arXiv comment6 pages, 4 figures, conference

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Attentive Statistics Pooling for Deep Speaker Embedding
• Deep Speaker: an End-to-End Neural Speaker Embedding System
• ESPnet: End-to-End Speech Processing Toolkit
• Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System
• The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods
• Exploiting Spectral Augmentation for Code-Switched Spoken Language Identification
• AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge