Gate Activation Signal Analysis for Gated Recurrent Neural Networks and its Correlation with Phoneme Boundaries

By Yu-Hsuan Wang, Cheng-Tao Chung, Hung-yi Lee. 2017

42 citations recorded by the source corpus.

In this paper we analyze the gate activation signals inside the gated recurrent neural networks, and find the temporal structure of such signals is highly correlated with the phoneme boundaries. This correlation is further verified by a set of experiments for phoneme segmentation, in which better results compared to standard approaches were obtained.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Model Architectures, Speech & Audio, 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 Electrical and Electronic Engineering

In Model Architectures

In Speech & Audio

In Signal Processing

Citations in the corpus

Semi-Supervised Speech Recognition via Local Prior Matching (2020, methodology): “Several methods can be used to estimate the text length on an unlabeled utterance, including the average speaking rate (Peng et al., 2019) or a phoneme/syllable segmentation (Adell & Bonafonte, 2004; Scharenborg et al., 2010; Wang et al., 2017).”
Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection (2018, methodology): “We see that the proposed SSAE performed significantly better than the other two methods on all languages except comparable to GAS for German.”
A Brief Overview of Unsupervised Neural Speech Representation Learning (2022, background): “In practice, this is often achieved implicitly, by learning segment boundaries or by taking repeated quantized values to belong to the same segment (Kamper and van Niekerk 2021; Chorowski et al. 2019a; Michel et al. 2017; Kreuk, Keshet, and Adi 2020; Wang, Chung, and Lee 2017; Dieleman et al. 2021).”
Completely Unsupervised Speech Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models (2019, methodology): “The lower section (III) is the case that the initial boundaries were obtained automatically with GAS [30].”
Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching (2018, methodology): “We follow the default hyper-parameters in Wang et al. (2017) to estimate the phoneme boundaries, which are used to initialize our algorithm.”
One Size Does Not Fit All: Comparing NMT Representations of Different Granularities (2019, methodology): “, 2018, among others), RNN states (Qian et al., 2016a; Shi et al., 2016; Wu and King, 2016; Wang et al., 2017), and NMT representations (Shi et al.”
Self-Supervised Speech Representation Learning: A Review (2022, unknown): “[266] MFCC GAS [267] Phoneme Empirical-ODM [268] Self-training TIMIT (PER): 41.”
What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models (2018, background): “…analyzing word and sentence embeddings (Adi et al. 2016; Qian, Qiu, and Huang 2016b; Conneau et al. 2018), recurrent neural network (RNN) states (Shi, Padhi, and Knight 2016; Wang, Chung, and Lee 2017), and NMT representations (Belinkov et al. 2017a; Belinkov et al. 2017b; Dalvi et al. 2017).”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, background): “Others have correlated activations of gated recurrent networks with phone boundaries in autoencoders [335] and in a text-to-speech system [345].”
Audio Word2vec: Sequence-to-Sequence Autoencoding for Unsupervised Learning of Audio Segmentation and Representation (2019, methodology): “We observe that SSAE significantly outperforms the other baselines on all languages other than German GAS, to which it is comparable.”