Front-End Factor Analysis For Speaker Verification

By Florin Curelaru. 2018

1,716 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, 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 Natural Language Processing

In Speech & Audio

In Signal Processing

Citations in the corpus

Jukebox: A Generative Model for Music (2020, methodology): “Ideas like clustering (Dehak et al., 2011), priming (Wang et al., 2018), and variational autoencoders (Hsu et al., 2019; Akuzawa et al., 2018) have been used to learn broader styles of speech and control expressivity in an unsupervised way.”
An Unsupervised Autoregressive Model for Speech Representation Learning (2019, methodology): “For speaker veriﬁcation, we follow the standard split of TIMIT, use the training set for training the universal background model, the i-vector extractor [29], a linear discriminant analysis (LDA) model.”
Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System (2018, background): “Inrecentdecades, the classical GMM i-vector approach and its variants have dominated multiple kinds of paralinguistic speech attribute recognition ﬁelds for its superior performance, simplicity and efﬁciency [3, 4].”
VoxCeleb2: Deep Speaker Recognition (2018, methodology): “Traditionally, the ﬁeld of speaker recognition has been dominated by i-vectors [17], classiﬁed us-ing techniques such as heavy-tailed PLDA [18] and Gauss-PLDA [19].”
Generalized End-to-End Loss for Speaker Verification (2017, methodology): “In this work, we focus on TI-SV and a particular subtask of TD-SV known as global password TD-SV, where the veriﬁcation is based on a detected keyword, e.g. “OK Google” [5, 6] In previous studies, i-vector based systems have been the dominating approach for both TD-SV and TI-SV applications [7].”
VoxCeleb: A Large-Scale Speaker Identification Dataset (2017, methodology): “Gender independent i-vector extractors [10] are trained on the VoxCeleb dataset to produce 400-dimensional i-vectors.”
End-to-end text-dependent speaker verification (2015, methodology): “For example, the combination of i-vector and probabilistic linear discriminant analysis (PLDA) [5, 6] has become the dominant approach, both for text-independent speaker veriﬁcation [7, 8, 5, 6] and text-dependent speaker veriﬁcation [9, 10, 11].”
Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data (2017, methodology): “We use the i-vector method [6] as the baseline, which is the representation used in most state-of-the-art speaker veriﬁcation systems.”
Zero-Shot Multi-Speaker Text-To-Speech with State-Of-The-Art Neural Speaker Embeddings (2019, background): “Villalba et al. summarized several state-of-the-art speaker recognition systems for the NIST SRE18 Challenge [16], where x-vector based systems [17] consistently outperformed i-vector based systems [18].”
Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering (2017, methodology): “Speciﬁcally, we are motivated by the ideas "i-vector" [Dehak et al., 2011] in speech recognition, where neural network based adaptation is performed among different (groups) of speakers and we focused instead on different types of questions here.”
The microsoft 2016 conversational speech recognition system (2016, methodology): “Speaker adaptive modeling in our system is based on conditioning the network on an i-vector [30] characterization of each speaker [22, 31].”
The CAPIO 2017 Conversational Speech Recognition System (2017, background): “Most of the research effort on neural network adaptation thus has been focused either to update a part of parameters while ﬁxing the rest [7, 8, 9, 10] or to append domain-speciﬁc features (e.g., i-vectors [11] in case of speaker adaptation) for a better feature transformation [12, 13, 14].”
Disentangled Sequential Autoencoder (2018, methodology): “In formulas, We also include two baseline results from Hsu et al. (2017): one used the i-vector method (Dehak et al., 2011) for feature extraction, and the other one used µ 1 and µ 2 (analogous to µ z and µ f in our case) from a trained FHVAE model on Mel-scale ﬁlter bank (FBank) features.”
Deep Speaker: an End-to-End Neural Speaker Embedding System (2017, methodology): “Since gender labels are not available in all our datasets, the evaluation here is not split by gender, unlike the NIST speaker recognition evaluations (SREs) in [3].”
Unspeech: Unsupervised Speech Context Embeddings (2018, neutral): “I-vectors [5] are well-known, popular speaker vectors.”
Speaker Adaptation in DNN-Based Speech Synthesis Using d-Vectors (2017, methodology): “In [8], the authors study three different forms of conducting speaker adaptation under a DNN-TTS framework: (1) using i-vectors [14] as speaker-id input feature for the DNN; (2) network manipulation; and (3) conversion of the predicted features using Gaussian mixture models (GMMs).”
A DNN-based Mandarin-Tibetan cross-lingual speech synthesis (2018, neutral): “An i-vector represents speaker identity [22].”
End-to-End Code-Switching TTS with Cross-Lingual Language Model (2020, methodology): “The i-vector based speaker embedding is obtained through factor analysis [34].”