Generalized Discriminant Methods for Improved X-Vector Back-end Based Stress Speech Recognition

Prasetio, Barlian Henryranu; Tamura, H.; Tanno, Koichi

doi:10.1541/ieejeiss.139.1341

Cited by 3 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fundamental frequency, energy, formats, mel-frequency cepstral coefficients (MFCC), and the Teager energy operator (TEO) are typical techniques used to capture stress and emotion features 34 . The identity vector (i-vector) and DNN embedding vector (x-vector) that have success in recognizing the speaker 35,36 and language 37,38 have also recently proven robust in representing the stress 13 and emotion features 39 .…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep time-delay Markov network for prediction and modeling the stress and emotions state transition

Prasetio

Tamura

Tanno

2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

To recognize stress and emotion, most of the existing methods only observe and analyze speech patterns from present-time features. However, an emotion (especially for stress) can change because it was triggered by an event while speaking. To address this issue, we propose a novel method for predicting stress and emotions by analyzing prior emotional states. We named this method the deep time-delay Markov network (DTMN). Structurally, the proposed DTMN contains a hidden Markov model (HMM) and a time-delay neural network (TDNN). We evaluated the effectiveness of the proposed DTMN by comparing it with several state transition methods in predicting an emotional state from time-series (sequences) speech data of the SUSAS dataset. The experimental results show that the proposed DTMN can accurately predict present emotional states by outperforming the baseline systems in terms of the prediction error rate (PER). We then modeled the emotional state transition using a finite Markov chain based on the prediction result. We also conducted an ablation experiment to observe the effect of different HMM values and TDNN parameters on the prediction result and the computational training time of the proposed DTMN.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The body reveals the stress response through facial expression, body language, and tone of voice. Thus, the facial expression 5 – 8 and speech of the stressed person 9 – 13 can be used to detect the level of stress 14 . Since the speech-based stress measurement method is non-invasive, it is convenient for measuring stress.…”

Section: Introductionmentioning

confidence: 99%

Deep time-delay Markov network for prediction and modeling the stress and emotions state transition

Prasetio

Tamura

Tanno

2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…We have built a stress speech recognition (SSR) system [36] to models the stress speech. This SSR model was trained using labeled stress speech utterances Y(y 1 , y 2 , .…”

Section: Stress Speech Recognition Model Based Pairwise Constraintsmentioning

confidence: 99%

Semi-Supervised Deep Time-Delay Embedded Clustering for Stress Speech Analysis

2019

Self Cite

View full text Add to dashboard Cite

Real stressed speech is affected by various aspects (individual characteristics and environment) so that the stress patterns are diverse and different on each individual. To this end, in our previous work, we performed an unsupervised clustering method that able to self-learning manner by mapping the feature representations of the stress speech and clustering tasks simultaneously, called deep time-delay embedded clustering (DTEC). However, DTEC has not confirmed yet the compatibility between the output class and informational classes. Therefore, we proposed semi-supervised time-delay embedded clustering (SDTEC) as a new framework of semi-supervised in DTEC. SDTEC incorporates the prior information of pairwise constraints in the embedding layer and simultaneously learns the feature representation and the clustering assignments. The prior information was used to guide the clustering procedure so that the points that belong to the incorrect cluster can be corrected. The effectiveness of the proposed SDTEC was evaluated by comparing it with some baseline methods in terms of the clustering error rate (CER). Moreover, to demonstrate SDTEC’s capabilities, we conducted a comprehensive ablation study. Based on experiment results, SDTEC outperformed the baseline methods and achieves state-of-the-art results in semi-supervised clustering.

show abstract

Embedded Discriminant Analysis based Speech Activity Detection for Unsupervised Stress Speech Clustering

Prasetio

Tamura

Tanno

2020

2020 Joint 9th International Conference on Informatics, Electronics &Amp; Vision (ICIEV) and 2020 4th International Conference

View full text Add to dashboard Cite

Generalized Discriminant Methods for Improved X-Vector Back-end Based Stress Speech Recognition

Cited by 3 publications

References 18 publications

Deep time-delay Markov network for prediction and modeling the stress and emotions state transition

Deep time-delay Markov network for prediction and modeling the stress and emotions state transition

Semi-Supervised Deep Time-Delay Embedded Clustering for Stress Speech Analysis

Embedded Discriminant Analysis based Speech Activity Detection for Unsupervised Stress Speech Clustering

Contact Info

Product

Resources

About