Robust Front-End Processing For Emotion Recognition In Noisy Speech

Pandharipande, Meghna; Chakraborty, Rupayan; Panda, Amlana; Kopparapu, Sunil Kumar

doi:10.1109/iscslp.2018.8706699

Cited by 9 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Evaluating Criterionmentioning

confidence: 99%

“…In experiment 1,we compared the methods mentioned in this paper with the previous methods in [8], [9], [10], and [11] on AVEC database and AFEW6.0 database to verify the advantages of our method in removing noise compared with other literatures. The methods used in [8], [9], [10], and [11] were described in the introduction. In the second experiment, the methods mentioned in this paper are compared with references [12], [13], [14], [15] on AVEC database and AFEW6.0 database in the field of eliminating the differences between different databases.…”

Section: Evaluating Criterionmentioning

confidence: 99%

“…They calculated the average histogram of pitch and MFCC, and then used it as a reference for equalization. In [10], speech activity detector (VAD) was used to discard prominent and noisy frames. The proposed VAD combined with nonnegative matrix decomposition technology played a key role in improving robustness.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Design of Efficient Speech Emotion Recognition Based on Multi Task Learning

Liu

Kexin

2023

IEEE Access

View full text Add to dashboard Cite

Speech emotion recognition technology includes feature extraction and classifier construction. However, the recognition efficiency is reduced due to noise interference and gender differences. To solve this problem, this paper used two multi-task learning models based on adversarial multi-task learning(ASP-MTL). The first model took emotion recognition as the main task and noise recognition as the auxiliary task, and removed the noise part identified by the auxiliary task. After identifying the non-noise part, the second model was constructed. The second model took emotion recognition as the main task and gender classification as the auxiliary task. These two multi-task learning models can not only can use shared information to learn the relationship between different tasks, but also can identify specific tasks. This paper used Audio/Visual Emotion Challenge (AVEC) database and AFEW6.0 database,which were recorded in the field environment. Considering the problem of data imbalance between datasets, the data balance operation was carried out on the data sets in the process of data preprocessing. The paper shows an increase of around 10% in terms of accuracy and F1 score with the recent works using AVEC database and AFEW6.0 datasets, which proved that this paper has made a great progress in SER.

show abstract

Section: Evaluating Criterionmentioning

confidence: 99%

Section: Evaluating Criterionmentioning

confidence: 99%

See 1 more Smart Citation

Design of Efficient Speech Emotion Recognition Based on Multi Task Learning

Liu

Kexin

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Relatively speaking, there are still few studies introducing noise environment. Researchers usually use front-end noise reduction [29], feature set design [30], multimodal recognition [31] and etc. to deal with noise.…”

Section: Related Workmentioning

confidence: 99%

“…Noise Injection Since researchers do not intentionally collect speech emotion data with noise, it is a general method for researching SER under noisy conditions to synthesize data with noise data set and clean speech emotion data set. We also synthesize noisy data like other related researchers have done [29], [31].…”

Section: Experiments a Pre-processingmentioning

confidence: 99%

Head Fusion: Improving the Accuracy and Robustness of Speech Emotion Recognition on the IEMOCAP and RAVDESS Dataset

Zhang²,

Zhang³

2021

IEEE Access

View full text Add to dashboard Cite

Speech Emotion Recognition (SER) refers to the use of machines to recognize the emotions of a speaker from his (or her) speech. SER benefits Human-Computer Interaction(HCI). But there are still many problems in SER research, e.g., the lack of high-quality data, insufficient model accuracy, little research under noisy environments, etc. In this paper, we proposed a method called Head Fusion based on the multi-head attention mechanism to improve the accuracy of SER. We implemented an attentionbased convolutional neural network(ACNN) model and conducted experiments on the Interactive Emotional Dyadic Motion Capture (IEMOCAP) data set. The accuracy is improved to 76.18% (weighted accuracy, WA) and 76.36% (unweighted accuracy, UA). To the best of our knowledge, compared with the state-ofthe-art result on this dataset (76.4% of WA and 70.1% of WA), we achieved a UA improvement of about 6% absolute while achieving a similar WA. Furthermore, We conducted empirical experiments by injecting speech data with 50 types of common noises. We inject the noises by altering the noise intensity, timeshifting the noises, and mixing different noise types, to identify their varied impacts on the SER accuracy and verify the robustness of our model. This work will also help researchers and engineers properly add their training data by using speech data with the appropriate types of noises to alleviate the problem of insufficient high-quality data.

show abstract