28 August 2019 in IEEE Access
Speech emotion recognition is a vital and challenging task that the feature extraction plays a significant role in the SER performance. With the development of deep learning, we put our eyes on the structure of end-to-end and authenticate the algorithm that is extraordinary effective. In this paper, we introduce a novel architecture ADRNN (dilated CNN with residual block and BiLSTM based on the attention mechanism) to apply for the speech emotion recognition which can take advantage of the strengths of diverse networks and overcome the shortcomings of utilizing alone, and are evaluated in the popular IEMOCAP database and Berlin EMODB corpus. Dilated CNN can assist the model to acquire more receptive fields than using the pooling layer. Then, the skip connection can keep more historic info from the shallow layer and BiLSTM layer are adopted to learn long-term dependencies from the learned local features. And we utilize the attention mechanism to enhance further extraction of speech features. Furthermore, we improve the loss function to apply softmax together with the center loss that achieves better classification performance. As emotional dialogues are transformed of the spectrograms, we pick up the values of the 3-D Log-Mel spectrums from raw signals and put them into our proposed algorithm and obtain a notable performance to get the 74.96% unweighted accuracy in the speaker-dependent and the 69.32% unweighted accuracy in the speaker-independent experiment. It is better than the 64.74% from previous state-of-the-art methods in the spontaneous emotional speech of the IEMOCAP database. In addition, we propose the networks that achieve recognition accuracies of 90.78% and 85.39% on Berlin EMODB of speaker-dependent and speaker-independent experiment respectively, which are better than the accuracy of 88.30% and 82.82% obtained by previous work. For validating the robustness and generalization, we also make an experiment for cross-corpus between above databases and get the preferable 63.84% recognition accuracy in final.
11 July 2022 in Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Digital health applications are becoming increasingly important for assessing and monitoring the wellbeing of people suffering from mental health conditions like depression. A common target of said applications is to predict the results of self-assessed Patient-Health-Questionnaires (PHQ), indicating current symptom severity of depressive individuals. Many of the currently available approaches to predict PHQ scores use passive data, e.g., from smartphones. However, there are several other scores and data besides PHQ, e.g., the Behavioral Activation for Depression Scale–Short Form (BADSSF), the Center for Epidemiologic Studies Depression Scale (CESD), or the Personality Dynamics Diary (PDD), all of which can be effortlessly collected on a daily basis. In this work, we explore the potential of using actively-collected data to predict and forecast daily PHQ-2 scores on a newly-collected longitudinal dataset. We obtain a best MAE of 1.417 for daily prediction of PHQ-2 scores, which specifically in the used dataset have a range of 0 to 12, using leave-one-subject-out cross-validation, as well as a best MAE of 1.914 for forecasting PHQ-2 scores using data from up to the last 7 days. This illustrates the additive value that can be obtained by incorporating actively-collected data in a depression monitoring application.
19 February 2021 in Bulletin Of The Polish Academy Of Sciences-Technical Sciences
Speech emotion recognition (SER) is a complicated and challenging task in the human-computer interaction because it is difficult to find the best feature set to discriminate the emotional state entirely. We always used the FFT to handle the raw signal in the process of extracting the low-level description features, such as short-time energy, fundamental frequency, formant, MFCC (mel frequency cepstral coefficient) and so on. However, these features are built on the domain of frequency and ignore the information from temporal domain. In this paper, we propose a novel framework that utilizes multi-layers wavelet sequence set from wavelet packet reconstruction (WPR) and conventional feature set to constitute mixed feature set for achieving the emotional recognition with recurrent neural networks (RNN) based on the attention mechanism. In addition, the silent frames have a disadvantageous effect on SER, so we adopt voice activity detection of autocorrelation function to eliminate the emotional irrelevant frames. We show that the application of proposed algorithm significantly outperforms traditional features set in the prediction of spontaneous emotional states on the IEMOCAP corpus and EMODB database respectively, and we achieve better classification for both speaker-independent and speaker-dependent experiment. It is noteworthy that we acquire 62.52% and 77.57% accuracy results with speaker-independent (SI) performance, 66.90% and 82.26% accuracy results with speaker-dependent (SD) experiment in final.
1 January 2019 in IEEE Access
6 May 2022 in IEEE Journal of Biomedical and Health Informatics
The importance of detecting whether a per- son wears a face mask while speaking has tremendously increased since the outbreak of SARS-CoV-2 (COVID-19), as wearing a mask can help to reduce the spread of the virus and mitigate the public health crisis. Besides affecting human speech characteristics related to frequency, face masks cause temporal interferences in speech, altering the pace, rhythm, and pronunciation speed. In this regard, this paper presents two effective neural network models to detect surgical masks from audio. The proposed architectures are both based on Convolutional Neural Net- works (CNNs), chosen as an optimal approach for the spatial processing of the audio signals. One architecture applies a Long Short-Term Memory (LSTM) network to model the time-dependencies. Through an additional attention mechanism, the LSTM-based architecture enables the extraction of more salient temporal information. The other architecture (named ConvTx) retrieves the relative position of a sequence through the positional encoder of a transformer module. In order to assess to which extent both architectures can complement each other when modelling temporal dynamics, we also explore the combination of LSTM and Transformers in three hybrid models. Finally, we also investigate whether data augmentation techniques, such as, using transitions between audio frames and considering gender-dependent frameworks might impact the performance of the proposed architectures. Our experimental results show that one of the hybrid models achieves the best performance, surpassing existing state-of-the-art results for the task at hand.