A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification

By Weicheng Cai, Zexin Cai, Xiangjinzi Zhang, Xiaoqi Wang, Ming Li. 2018

79 citations recorded by the source corpus.

A novel learnable dictionary encoding layer is proposed in this paper for end-to-end language identification. It is inline with the conventional GMM i-vector approach both theoretically and practically. We imitate the mechanism of traditional GMM training and Supervector encoding procedure on the top of CNN. The proposed layer can accumulate high-order statistics from variable-length input sequence and generate an utterance level fixed-dimensional vector representation. Unlike the conventional methods, our new approach provides an end-to-end learning framework, where the inherent dictionary are learned directly from the loss function. The dictionaries and the encoding representation for the classifier are learned jointly. The representation is orderless and therefore appropriate for language identification. We conducted a preliminary experiment on NIST LRE07 closed-set task, and the results reveal that our proposed dictionary encoding layer achieves significant error reduction comparing with the simple average pooling.

Subfields: Artificial Intelligence, Natural Language Processing, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Signal Processing

Citations in the corpus

Object-Centric Learning with Slot Attention (2020, methodology): “Variants of soft k-means clustering with learnable, cluster-specific parameters have been introduced in the computer vision [74] and speech recognition communities [75], but they differ from our approach in that they do not use a recurrent, multi-step update, and do not respect permutation symmetry ”
Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System (2018, methodology): “In our previous works [24, 25], we proposed a learnable dictionary encoding (LDE) layer, which connects the conventional GMM Supervector procedure and state-of-the-art end-to-end neural network together.”
Voxceleb: Large-scale speaker verification in the wild (2020, methodology): “Typically, such systems are trained end-to-end for classi ﬁ cation with a softmax loss (Okabe et al., 2018) or one of its variants, such as the angular softmax (Cai et al., 2018c).”
Utterance-level Aggregation for Speaker Recognition in the Wild (2019, methodology): “The ﬁnal pooling strategy of interest is the Learnable Dictionary Encoding (LDE) proposed by [14, 15].”
Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS? (2020, background): “Dialect identification can be considered as a subtask of spoken language recognition, and in general, approaches from speaker recognition tasks can be directly transferred to dialect identification, see [24, 25, 26, 27].”