Improving acoustic based keyword spotting using LVCSR lattices

Motlíček, Petr; Valente, Fabio; Szöke, Igor

doi:10.1109/icassp.2012.6288898

Cited by 28 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the conventional ASR decoder parameters to obtain word recognition lattices [14] (beam width of 13). The same type of lattices has been used previously for various tasks [22,23,24]. From these lattices, we obtain the senone posteriors, by fixing the acoustic scale parameter to 0.01, in order to obtain i-vectors that follow a Gaussian distribution.…”

Section: Asr Systemmentioning

confidence: 99%

Content Normalization for Text-Dependent Speaker Verification

et al. 2017

Self Cite

View full text Add to dashboard Cite

Subspace based techniques, such as i-vector and Joint Factor Analysis (JFA) have shown to provide state-of-the-art performance for fixed phrase based text-dependent speaker verification. However, the error rates of such systems on the random digit task of RSR dataset are higher than that of Gaussian Mixture Model-Universal Background Model (GMM-UBM). In this paper, we aim at improving i-vector system by normalizing the content of the enrollment data to match the test data. We estimate i-vectors for each frames of a speech utterance (also called online i-vectors). The largest similarity scores across frames between enrollment and test are taken using these online i-vectors to obtain speaker verification scores. Experiments on Part3 of RSR corpora show that the proposed approach achieves 12% relative improvement in equal error rate over a GMM-UBM based baseline system.

show abstract

Section: Asr Systemmentioning

confidence: 99%

Content Normalization for Text-Dependent Speaker Verification

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Pham et al [3] proposed the system and keyword dependent fusion method SKDWCombMNZ in 2014, which ourperformed other arithmetic-based methods. Discriminative system fusion methods employing classifiers have been explored in [3,4,5]. With large number of features from lattices and detection lists, discriminative fusion can often achieve inspiring performance.…”

Section: Introductionmentioning

confidence: 99%

Improved system fusion for keyword search

Cai

Lü

et al. 2015

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

View full text Add to dashboard Cite

It has been demonstrated that system fusion can significantly improve the performance of keyword search. In this paper, we compare the performance of several widely-used arithmeticbased fusion methods using different normalization pipeline and try to find the best pipeline. A novel arithmetic-based fusion method is proposed in this work. The method supplies a more effective way to incorporate the number of systems which have non-zero scores for a detection. When tested on the development test dataset of the OpenKWS15 Evaluation, the proposed method achieves the highest maximum termweighted value (MTWV) and actual term-weighted value (ATWV) among all other arithmetic-based fusion methods. Usually, discriminative fusion methods employing classifiers can outperform arithmetic-based fusion methods. A DNNbased fusion method is explored in this work. After wordburst information is added, the DNN-based fusion method outperforms all other methods. In addition, it is notable that our arithmetic-based method achieves the same MTWV as the DNN-based method.

show abstract

“…In [2], confusion garbage model was developed to absorb similar pronunciation words confused with the specific keywords of a task. The combination of acoustic and LVCSR based keyword system was proposed as a method that the lattice generated from LVCSR was used to improve performance [3]. Even there are so many methods, the most widely used is the calculation and optimization of confidence measure.…”

Section: Introductionmentioning

confidence: 99%

Improved keyword spotting system by optimizing posterior confidence measure vector using feed-forward neural network

Liu

Cai

2014

2014 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

In this paper, a novel method based on feedforward neural network is proposed to optimize the confidence measure for improving a mandarine keyword spotting system. Keyword spotting is to detect the occurrences of a pre-defined list of keywords in the input speech, and confidence measure is an critical part in the verification stage of keyword spotting. Posterior confidence has been widely used and was verified to be effective. In some previous works, the optimization of posterior confidence has been proposed, which linearly transforms the phone-level confidence into the word-level confidence. On this basis, we propose a neural network based method that make a non-linear transformation. In addition, a sparse activation and back-propagation strategy is proposed to make this method feasible and work fast. In the experiments, the proposed method is compared to other two previous methods. To evaluate performance, two most commonly used measures are considered: AUC and EER. The experimental result shows that the proposed method is effective and achieved the best performance among three methods.

show abstract

Improving acoustic based keyword spotting using LVCSR lattices

Cited by 28 publications

References 8 publications

Content Normalization for Text-Dependent Speaker Verification

Content Normalization for Text-Dependent Speaker Verification

Improved system fusion for keyword search

Improved keyword spotting system by optimizing posterior confidence measure vector using feed-forward neural network

Contact Info

Product

Resources

About