A Transfer Learning Method For Speech Emotion Recognition From Automatic Speech Recognition

Abstract

This paper presents a transfer learning method in speech emotion recognition based on a Time-Delay Neural Network (TDNN) architecture. A major challenge in the current speech-based emotion detection research is data scarcity. The proposed method resolves this problem by applying transfer learning techniques in order to leverage data from the automatic speech recognition (ASR) task for which ample data is available. Our experiments also show the advantage of speaker-class adaptation modeling techniques by adopting identity-vector (i-vector) based features in addition to standard Mel-Frequency Cepstral Coefficient (MFCC) features.[1] We show the transfer learning models significantly outperform the other methods without pretraining on ASR. The experiments performed on the publicly available IEMOCAP dataset which provides 12 hours of motional speech data. The transfer learning was initialized by using the Ted-Lium v.2 speech dataset providing 207 hours of audio with the corresponding tran

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhou2020a

Related papers

• Multi-modal Emotion Detection With Transfer Learning (2020)0.00
• Transfer Learning For Improving Speech Emotion Classification Accuracy (2018)15.10
• Multimodal Emotion Recognition Using Transfer Learning From Speaker Recognition And Bert-based Models (2022)12.10
• Deep Learning Based Emotion Recognition System Using Speech Features And Transcriptions (2019)0.00
• Asr-based Features For Emotion Recognition: A Transfer Learning Approach (2018)9.76
• Emodiarize: Speaker Diarization And Emotion Identification From Speech Signals Using Convolutional Neural Networks (2023)0.00
• Embedded Emotions -- A Data Driven Approach To Learn Transferable Feature Representations From Raw Speech Input For Emotion Recognition (2020)0.00
• Attention Based Fully Convolutional Network For Speech Emotion Recognition (2018)15.25