Speaker adaptation of neural network acoustic models using i-vectors

Saon, George; Soltau, Hagen; Nahamoo, D.; Picheny, Michael

doi:10.1109/asru.2013.6707705

Cited by 569 publications

(392 citation statements)

References 13 publications

Supporting

Mentioning

384

Contrasting

Unclassified

Order By: Relevance

“…(3) As ability to express complex objective functions in network, shallow structure neural network sometimes cannot well realize the complex high-dimensional function. (4) In terms of computational complexity of the network structure, with the depth of k compact network structure to express a certain function, in the depth of less than the network structure to express the function of k, it may need to increase the number of the exponential scale factor calculation, greatly increase the complexity of the calculation [31][32][33][34].…”

Section: The Modified Deep Convolution Neural Networkmentioning

confidence: 99%

A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology

Huang¹,

Zhang²

2017

Journal of Electrical Engineering and Technology

View full text Add to dashboard Cite

-This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

show abstract

Section: The Modified Deep Convolution Neural Networkmentioning

confidence: 99%

A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology

Huang¹,

Zhang²

2017

Journal of Electrical Engineering and Technology

View full text Add to dashboard Cite

show abstract

“…Among them, establishing a more appropriate combination of frame posteriors obtained in DNNs; exploring different fusions among DNNs and ivector systems [39]; and dealing with unbalanced training data. Note that even though we proposed different ways of combining posteriors, all of them were blind (no need for training), as we focused on real-time applications and simple approaches.…”

Section: Future Workmentioning

confidence: 99%

Frame-by-frame language identification in short utterances using deep neural networks

et al. 2015

View full text Add to dashboard Cite

Esta es la versión de autor del artículo publicado en: This is an author produced version of a paper published in:Neural Networks 64 (2015) AbstractThis work addresses the use of deep neural networks (DNNs) in automatic language identification (LID) focused on short test utterances. Motivated by their recent success in acoustic modelling for speech recognition, we adapt DNNs to the problem of identifying the language in a given utterance from the short-term acoustic features. We show how DNNs are particularly suitable to perform LID in real-time applications, due to their capacity to emit a language identification posterior at each new frame of the test utterance. We then analyse different aspects of the system, such as the amount of required training data, the number of hidden layers, the relevance of contextual information and the effect of the test utterance duration. Finally, we propose several methods to combine frame-by-frame posteriors. Experiments are conducted on two different datasets: the public NIST Language Recognition Evaluation 2009 (3 seconds task) and a much larger corpus (of 5 million utterances) known as Google 5M LID, obtained from different Google Services. Reported results show relative improvements of DNNs versus the i-vector system of 40% in LRE09 3 second task and 76% in Google 5M LID.

show abstract

“…Some studies [22], [23] have shown that performance can be improved by supplying complementary features as inputs to the network in parallel with the regular acoustic features for speech recognition. Motivated by the above work, we propose augmenting the acoustic features from microphone array with the spatial information to further improve the performance of multichannel speech recognition.…”

Section: Introductionmentioning

confidence: 99%

Improve Multichannel Speech Recognition with Temporal and Spatial Information

Zhang

Zhao

2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this letter, we explored the usage of spatio-temporal information in one unified framework to improve the performance of multichannel speech recognition. Generalized cross correlation (GCC) is served as spatial feature compensation, and an attention mechanism across time is embedded within long short-term memory (LSTM) neural networks. Experiments on the AMI meeting corpus show that the proposed method provides a 8.2% relative improvement in word error rate (WER) over the model trained directly on the concatenation of multiple microphone outputs.

show abstract

Speaker adaptation of neural network acoustic models using i-vectors

Cited by 569 publications

References 13 publications

A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology

A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology

Frame-by-frame language identification in short utterances using deep neural networks

Improve Multichannel Speech Recognition with Temporal and Spatial Information

Contact Info

Product

Resources

About