iVector-based discriminative adaptation for automatic speech recognition

By Martin Karafiát, Lukáš Burget, Pavel Matejka, Ondrej Glembek, Jan Honza Cernocký. 2011

96 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Speech & Audio

In Signal Processing

Citations in the corpus

ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context (2020, background): “Previous works on hybrid ASR have successfully introduced the context to acoustic models by either stacking a large number of layers, or having a separately trained global vector to represent the speaker and the environment information [13, 14, 15, 16].”
An analysis of environment, microphone and data simulation mismatches in robust speech recognition (2017, unknown): “This is widely recognized as good practice and many solutions are available to improve robustness to this mismatch (Gales, 1998; Shinoda, 2011; Karaﬁ´at et al., 2011; Swietojanski and Renals, 2014).”
Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors (2015, methodology): “work [47], [13], [38], [17] has applied i-vectors successfully to”
Speaker adaptation of neural network acoustic models using i-vectors (2013, methodology): “A concatenation of i-vectors and ASR features is used in [9] for discriminative speaker adaptation with region dependent linear transforms.”
JHU Kaldi system for Arabic MGB-3 ASR challenge using diarization, audio-transcript alignment and transfer learning (2017, methodology): “The system also uses i-vectors for speaker adaptation [11] using speaker information obtained from section 2.”
Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models (2014, methodology): “The i-vectors can be regarded as the basis vectors which span a subspace of speaker variability, and were first used for adaptation in a GMM framework by Karafiat et al [22].”
A time delay neural network architecture for efficient modeling of long temporal contexts (2015, background): “iVectors which capture both speaker and environment specific information have been shown to be useful for instantaneous and discriminative adaptation of the neural network [5, 6].”
JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS (2015, background): “…and DARPA BOLT Contract No HR0011-12-C-0015. iVectors which capture both speaker and environment speciﬁc information have been shown to be useful for rapid adaptation of the neural network [4, 5, 6]. iVector based adaptation has also been shown to be effective in reverberant environments [7].”
Acoustic Modeling for Overlapping Speech Recognition: Jhu Chime-5 Challenge System (2019, methodology): “I-vectors are used for speaker adaptation [24, 25] with the i-vectors being extracted on top of PCA-reduced spliced-MFCC features.”
Multimodal Intelligence: Representation Learning, Information Fusion, and Applications (2019, unknown): “downstream tasks nowadays [86]–[97].”