Transfer Learning for Improving Speech Emotion Classification Accuracy

Latif, Siddique; Rana, Rajib; Younis, Shahzad; Qadir, Junaid; Epps, Julien

doi:10.21437/interspeech.2018-1625

Cited by 108 publications

(51 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [9,10,11,12], adversarial learning paradigm * Both the authors contributed equally to this paper is explored for robust recognition. In [13,14], transfer learning approach is explored.…”

Section: Introductionmentioning

confidence: 99%

X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition

Pappagari

Wang

Villalba

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this work, we explore the dependencies between speaker recognition and emotion recognition. We first show that knowledge learned for speaker recognition can be reused for emotion recognition through transfer learning. Then, we show the effect of emotion on speaker recognition. For emotion recognition, we show that using a simple linear model is enough to obtain good performance on the features extracted from pre-trained models such as the x-vector model. Then, we improve emotion recognition performance by finetuning for emotion classification. We evaluated our experiments on three different types of datasets: IEMOCAP, MSP-Podcast, and Crema-D. By fine-tuning, we obtained 30.40%, 7.99%, and 8.61% absolute improvement on IEMOCAP, MSP-Podcast, and Crema-D respectively over baseline model with no pre-training. Finally, we present results on the effect of emotion on speaker verification. We observed that speaker verification performance is prone to changes in test speaker emotions. We found that trials with angry utterances performed worst in all three datasets. We hope our analysis will initiate a new line of research in the speaker recognition community.

show abstract

“…In [9,10,11,12], adversarial learning paradigm * Both the authors contributed equally to this paper is explored for robust recognition. In [13,14], transfer learning approach is explored.…”

Section: Introductionmentioning

confidence: 99%

X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition

Pappagari

Wang

Villalba

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…making it difficult to avoid speaker adaptation. Fully supervised techniques trained on such datasets hence often demonstrate high accuracy for only intra-corpus data, with a natural propensity to overfit [42].…”

Section: Introductionmentioning

confidence: 99%

Emotion Recognition in Speech using Cross-Modal Transfer in the Wild

Albanie

Nagrani

Vedaldi

et al. 2018

Proceedings of the 26th ACM International Conference on Multimedia

249

126

View full text Add to dashboard Cite

“…Research on speech emotion recognition primarily focuses on hand-engineered acoustic features as well as on designing e cient machine learning based models for accurate emotion prediction [6,7]. In particular, building an appropriate feature representation and designing an appropriate classi er for these features have o en been treated as separate problems in the speech recognition community.…”

Section: Introductionmentioning

confidence: 99%

Direct Modelling of Speech Emotion from Raw Speech

et al. 2019

Self Cite

View full text Add to dashboard Cite

Speech emotion recognition is a challenging task and heavily depends on hand-engineered acoustic features, which are typically cra ed to echo human perception of speech signals. However, a lter bank that is designed from perceptual evidence is not always guaranteed to be the best in a statistical modelling framework where the end goal is for example emotion classi cation. is has fuelled the emerging trend of learning representations from raw speech especially using deep learning neural networks. In particular, a combination of Convolution Neural Networks (CNNs) and Long Short Term Memory (LSTM) have gained great traction for the intrinsic property of LSTM in learning contextual information crucial for emotion recognition; and CNNs been used for its ability to overcome the scalability problem of regular neural networks. In this paper, we show that there are still opportunities to improve the performance of emotion recognition from the raw speech by exploiting the properties of CNN in modelling contextual information. We propose the use of parallel convolutional layers to harness multiple temporal resolutions in the feature extraction block that is jointly trained with the LSTM based classication network for the emotion recognition task. Our results suggest that the proposed model can reach the performance of CNN trained with hand-engineered features from both IEMO-CAP and MSP-IMPROV datasets.

show abstract

Transfer Learning for Improving Speech Emotion Classification Accuracy

Cited by 108 publications

References 25 publications

X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition

X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition

Emotion Recognition in Speech using Cross-Modal Transfer in the Wild

Direct Modelling of Speech Emotion from Raw Speech

Contact Info

Product

Resources

About