An i-Vector PLDA based gender identification approach for severely distorted and multilingual DARPA RATS data

Ranjan, Shivesh; Liu, Gang; Hansen, John H. L.

doi:10.1109/asru.2015.7404813

Cited by 13 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An analysis of the trained CNNs showed that depending upon the kernel width of the first convolution layer either formant information or both fundamental frequency and formant information is modeled by the CNNs for gender recognition. In recent years, features such as i-vectors have been used for gender recognition [10]. In [26], a comparison between the proposed CNN-based approach and ivector based approach has been investigated for identifying gender under noisy conditions.…”

Section: Resultsmentioning

confidence: 99%

“…Building on this point, typically in the literature [3,4,5,6,7,8], two broad classes of features are used for this task: fundamental frequency (F0) and short term features like mel frequency cepstrum coefficients (MFCCs). There are also works that have investigated high level representations like Gaussian mixture model supervector [9,8] and i-vectors [10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On Learning to Identify Genders from Raw Speech Signal Using CNNs

Kabil¹,

Muckenhirn²,

Magimai.-Doss³

2018

Interspeech 2018

View full text Add to dashboard Cite

Automatic Gender Recognition (AGR) is the task of identifying the gender of a speaker given a speech signal. Standard approaches extract features like fundamental frequency and cepstral features from the speech signal and train a binary classifier. Inspired from recent works in the area of automatic speech recognition (ASR), speaker recognition and presentation attack detection, we present a novel approach where relevant features and classifier are jointly learned from the raw speech signal in end-to-end manner. We propose a convolutional neural networks (CNN) based gender classifier that consists of: (1) convolution layers, which can be interpreted as a feature learning stage and (2) a multilayer perceptron (MLP), which can be interpreted as a classification stage. The system takes raw speech signal as input, and outputs gender posterior probabilities. Experimental studies conducted on two datasets, namely AVspoof and ASVspoof 2015, with different architectures show that with simple architectures the proposed approach yields better system than standard acoustic features based approach. Further analysis of the CNNs show that the CNNs learn formant and fundamental frequency information for gender identification.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

On Learning to Identify Genders from Raw Speech Signal Using CNNs

Kabil¹,

Muckenhirn²,

Magimai.-Doss³

2018

Interspeech 2018

View full text Add to dashboard Cite

show abstract

“…Gender classification from speech is considered a solved problem on clean and monolingual corpora such as the TIMIT [6] speech corpus or distorted and multilingual corpora such as DARPA RATS [7]. However, differentiating the gender of children from speech is still challenging.…”

Section: Introductionmentioning

confidence: 99%

Gender aware spoken language translation applied to English-Arabic

Elaraby

Tawfik

Khaled

et al. 2018

2018 2nd International Conference on Natural Language and Speech Processing (ICNLSP)

View full text Add to dashboard Cite

Spoken Language Translation (SLT) is becoming more widely used and becoming a communication tool that helps in crossing language barriers. One of the challenges of SLT is the translation from a language without gender agreement to a language with gender agreement such as English to Arabic. In this paper, we introduce an approach to tackle such limitation by enabling a Neural Machine Translation system to produce gender-aware translation. We show that NMT system can model the speaker/listener gender information to produce gender-aware translation. We propose a method to generate data used in adapting a NMT system to produce gender-aware. The proposed approach can achieve significant improvement of the translation quality by 2 BLEU points.

show abstract

“…Being an important speaker-specific attribute, gender information is well preserved in the i-Vectors [14]. Most state-ofthe-art SID systems use a gender dependent approach where either part, or all of the SID pipeline can be gender dependent to obtain more competitive results.…”

Section: Introductionmentioning

confidence: 99%

Improved Gender Independent Speaker Recognition Using Convolutional Neural Network Based Bottleneck Features

Ranjan

Hansen

2017

Interspeech 2017

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel framework to improve performance of gender independent i-Vector PLDA based speaker recognition using convolutional neural network (CNN). Convolutional layers of a CNN offer robustness to variations in input features including those due to gender. A CNN is trained for ASR with a linear bottleneck layer. Bottleneck features extracted using the CNN are then used to train a gender-independent UBM to obtain frame posteriors for training an i-Vector extractor matrix. To preserve speaker specific information, a hybrid approach to training the i-Vector extractor matrix using MFCC features with corresponding frame posteriors derived from bottleneck features is proposed. On the NIST SRE10 C5 condition pooled trials, our approach reduces the EER and minDCF 2010 by +14.62% and +14.42% respectively compared to a standard mfcc based gender-independent speaker recognition system.

show abstract

An i-Vector PLDA based gender identification approach for severely distorted and multilingual DARPA RATS data

Cited by 13 publications

References 16 publications

On Learning to Identify Genders from Raw Speech Signal Using CNNs

On Learning to Identify Genders from Raw Speech Signal Using CNNs

Gender aware spoken language translation applied to English-Arabic

Improved Gender Independent Speaker Recognition Using Convolutional Neural Network Based Bottleneck Features

Contact Info

Product

Resources

About