Deep Neural Network Approaches to Speaker and Language Recognition

By Fred Richardson, Douglas A. Reynolds, Najim Dehak. 2015

434 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Signal Processing

Citations in the corpus

Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System (2018, background): “…perceptual linear prediction (PLP), shifted delta coefﬁ-cients (SDC) features [2, 5], and automatically learned phoneme discriminant features from deep neural networks (DNN), such as bottleneck features [6, 7, 8], phoneme posterior probability (PPP) features [9], and tandem features [10, 11].”
End-to-end text-dependent speaker verification (2015, background): “Hybrid approaches that include deep learning based components have also proved to be beneficial for text-independent speaker recognition [12, 13, 14].”
Less-forgetful Learning for Domain Expansion in Deep Neural Networks (2017, background): “Deep neural networks (DNNs) have advanced to nearly human levels of object, face, and speech recognition (Taigman et al. 2014) (Graves, Mohamed, and Hinton 2013) (Szegedy et al. 2014) (Simonyan and Zisserman 2014) (Zhang et al. 2016) (Richardson, Reynolds, and Dehak 2015).”
Deep neural network-based speaker embeddings for end-to-end speaker verification (2016, positive): “Recently, this paradigm has been improved by incorporating deep neural network (DNN) acoustic models [8, 9, 10, 11, 12].”
Learning Speaker Representations with Mutual Information (2018, background): “Deep learning has shown remarkable success in numerous speech tasks, including speech recognition [1–4] and speaker recognition [5, 6].”
DeepPano: Deep Panoramic Representation for 3-D Shape Recognition (2015, methodology): “…different from most of the methods mentioned above that use hand-crafted features, we learn the representation from data with a variant of CNN. Deeply learned representations are widely used and have achieved superior performance in many pattern recognition and signal processing tasks [11]–[13].”
Deep-ECG: Convolutional Neural Networks for ECG biometric recognition (2019, background): “Regarding one-dimensional signals, deep techniques have obtained promising results for recognition [35, 14].”
A survey of deep neural network architectures and their applications (2017, background): “achievements have also been obtained in ASR, especially in distant talking situations [132,161,164], audio-visual speech recognition (AVSR) systems [125], and data augmentation on the basis of labelpreserving transformations [27].”
End-to-End attention based text-dependent speaker verification (2016, background): “Two types of DNNs, speaker discriminant DNNs [6] and phonetic discriminant DNNs [14], have been investigated to extract the”
Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning (2018, methodology): “This method is widely used in various applications such as phoneme recognition [15], speaker recognition [15], and language recognition [16, 17].”
Speaker Recognition from Raw Waveform with SincNet (2018, background): “Deep learning has shown remarkable success in numerous speech tasks [4–7], including recent studies in speaker recognition [8, 9].”
Spoken Language Recognition using X-vectors (2018, methodology): “This is generally done in one of two ways: either pos-teriors from the ASR DNN replace those from a Gaussian mixture model (GMM) or the i-vector system is trained on bottleneck features extracted from the DNN [2, 3, 4, 5, 6].”
Deep Neural Network Embeddings for Text-Independent Speaker Verification (2017, background): “Recent work has shown that incorporating an ASR DNN acoustic model can improve the UBM’s ability to model phonetic content [8, 9, 10, 11, 12].”
LID-Senones and Their Statistics for Language Identification (2018, background): “[4], have demonstrated their capabilities in several related fields to infer powerful feature extraction layers.”
A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification (2018, background): “Each component in the dictionary represents a phoneme (or senone) physically, and the statistics is accumulated through senone posteriors, as is done in recently popular DNN i-vector approach [8, 9, 10].”
Speaker recognition based on deep learning: An overview (2020, methodology): “One can find that no matter whether we apply BNF alone [41] or concatenate it with other acoustic features [39], DNN-BNF/i-vector can significantly outperform the conventional GMM/i-vector, which indicates the effectiveness of the framework [36].”
Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification (2018, background): “Also, hybrid approaches that incorporate deep neural networks (DNNs) trained for automatic speech recognition (ASR) into the i-vector system have proved to be beneficial in some conditions [6, 7, 8, 9, 10].”
A Semisupervised Approach for Language Identification based on Ladder Networks (2016, methodology): “DNNs have also been applied to directly train language classification systems [4][5].”