Using Voice Quality Features to Improve Short-Utterance, Text-Independent Speaker Verification Systems

Park, Soo‐Jin; Yeung, Gary; Kreiman, Jody; Keating, Patricia; Alwan, Abeer

doi:10.21437/interspeech.2017-157

Cited by 20 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CPP, a measure of signal periodicity, replaced the harmonicto-noise ratios. This set of features was effectively applied to automatic speaker verification [41,1]. The features were extracted every 10ms using VoiceSauce software [42].…”

Section: Voice Quality Features (Vqual)mentioning

confidence: 99%

Effectiveness of Voice Quality Features in Detecting Depression

et al. 2018

Self Cite

View full text Add to dashboard Cite

Automatic assessment of depression from speech signals is affected by variabilities in acoustic content and speakers. In this study, we focused on addressing these variabilities. We used a database comprised of recordings of interviews from a large number of female speakers: 735 individuals suffering from depressive (dysthymia and major depression) and anxiety disorders (generalized anxiety disorder, panic disorder with or without agoraphobia) and 953 healthy individuals. Leveraging this unique and extensive database, we built an i-vector framework. In order to capture various aspects of speech signals, we used voice quality features in addition to conventional cepstral features. The features (F0, F1, F2, F3, H1-H2, H2-H4, H4-H2k, A1, A2, A3, and CPP) were inspired by a psychoacoustic model of voice quality [1]. An i-vector-based system using Mel Frequency Cepstral Coefficients (MFCCs) and another using voice quality features was developed. Voice quality features performed as well as MFCCs. A score-level fusion was then used to combine these two systems, resulting in a 6% relative improvement in accuracy in comparison with the i-vector system based on MFCCs alone. The system was robust even when the duration of the utterances was shortened to 10 seconds.

show abstract

Section: Voice Quality Features (Vqual)mentioning

confidence: 99%

Effectiveness of Voice Quality Features in Detecting Depression

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although within-speaker variability in phonetic content and speaking style degrades the performance of speaker verification systems for short utterances [27], due to the practical complexity of the CNN architecture and the vast number of parameters that need to be trained, it is not feasible to feed the utterances to the network since it will drastically reduce the number of samples in the training set. To compensate for this shortcoming, we propose to compute the prosodic features from the whole utterances.…”

Section: Prosodic Features To Enhance Deep Coupled Cnnmentioning

confidence: 99%

Prosodic-Enhanced Siamese Convolutional Neural Networks for Cross-Device Text-Independent Speaker Verification

Soleymani

Dabouei

Iranmanesh

et al. 2018

2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS)

View full text Add to dashboard Cite

In this paper a novel cross-device text-independent speaker verification architecture is proposed. Majority of the state-of-the-art deep architectures that are used for speaker verification tasks consider Mel-frequency cepstral coefficients. In contrast, our proposed Siamese convolutional neural network architecture uses Mel-frequency spectrogram coefficients to benefit from the dependency of the adjacent spectro-temporal features. Moreover, although spectro-temporal features have proved to be highly reliable in speaker verification models, they only represent some aspects of short-term acoustic level traits of the speaker's voice. However, the human voice consists of several linguistic levels such as acoustic, lexicon, prosody, and phonetics, that can be utilized in speaker verification models. To compensate for these inherited shortcomings in spectrotemporal features, we propose to enhance the proposed Siamese convolutional neural network architecture by deploying a multilayer perceptron network to incorporate the prosodic, jitter, and shimmer features. The proposed endto-end verification architecture performs feature extraction and verification simultaneously. This proposed architecture displays significant improvement over classical signal processing approaches and deep algorithms for forensic crossdevice speaker verification.

show abstract

“…These voice quality parameters were utilized to represent speaker identity, and improved automatic speaker verification system performance [19,20,21]. The feature set used in this study, denoted as VQual, included F0, F1, F2, F3, harmonic amplitude differences H1-H2, H2-H4, H4-H2k, formant amplitudes A1, A2, A3, and cepstral peak prominence (CPP, [22]).…”

Section: Vqual: Voice Quality Featuresmentioning

confidence: 99%

Using Voice Quality Supervectors for Affect Identification

Park

Afshan

Chua³

et al. 2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

The voice quality of speech sounds often conveys perceivable information about the speaker's affect. This study proposes perceptually important voice quality features to recognize affect represented in speech excerpts from individuals with mental, neurological, and/or physical disabilities. The voice quality feature set consists of F0, harmonic amplitude differences between the first, second, fourth harmonics and the harmonic near 2 kHz, the center frequency and amplitudes of the first 3 formants, and cepstral peak prominence. The feature distribution of each utterance was represented with a supervector, and the Gaussian mixture model and support vector machine classifiers were used for affect classification. Similar classification systems using the MFCCs and ComParE16 feature set were implemented. The systems were fused by taking the confidence mean of the classifiers. Applying the fused system to the Interspeech 2018 Atypical Affect subchallenge task resulted in unweighted average recalls of 43.9% and 41.0% on the development and test dataset, respectively. Additionally, we investigated clusters obtained by unsupervised learning to address gender-related differences.

show abstract

Using Voice Quality Features to Improve Short-Utterance, Text-Independent Speaker Verification Systems

Cited by 20 publications

References 20 publications

Effectiveness of Voice Quality Features in Detecting Depression

Effectiveness of Voice Quality Features in Detecting Depression

Prosodic-Enhanced Siamese Convolutional Neural Networks for Cross-Device Text-Independent Speaker Verification

Using Voice Quality Supervectors for Affect Identification

Contact Info

Product

Resources

About