BiLSTM-CNN Hyperparameter Optimization for Speech Emotion and Stress Recognition

Agustinus Bimo Gumelar, Eko Mulyanto Yuniarno, Derry Pramono Adi, Adri Gabriel Sooai, Indar Sugiarto, Mauridhi Hery Purnomo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

The most automated speech recognition (ASR) systems are extremely complicated, integrating many approaches and requiring a high variety of tuning parameters. Deep understanding and experience of each component are required to achieve optimal performance in ASR, confining the development of ASR systems to the experts. Hyperparameters are crucial for machine learning algorithms because they directly regulate the behavior of training algorithms and have a major impact on model performance. As a result, developing an effective hyperparameter optimization technique to optimize any given machine learning method would considerably increase machine learning efficiency. This work investigates the use of Random Forest and Bayesian to automatically optimize BiLSTM-CNN systems. We built the ASR based on the BiLSTM-CNN model and customized its hyperparameters value to heed our low-hardware specification during optimization. Furthermore, we gathered 1,000 clips of speech data from various movies, classifying them according to emotion and stress classes. In pursuit of contextual-level understanding in our ASR, we transcribed our speech data and used the bigram textual feature. Our Random Forest-optimized BiLSTM-CNN model ultimately reaches 84% of accuracy result and learning runtime in under 17 seconds.

Original languageEnglish
Title of host publicationInternational Electronics Symposium 2021
Subtitle of host publicationWireless Technologies and Intelligent Systems for Better Human Lives, IES 2021 - Proceedings
EditorsAndhik Ampuh Yunanto, Artiarini Kusuma N, Hendhi Hermawan, Putu Agus Mahadi Putra, Farida Gamar, Mohamad Ridwan, Yanuar Risah Prayogi, Maretha Ruswiansari
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages156-161
Number of pages6
ISBN (Electronic)9781665443463
DOIs
Publication statusPublished - 29 Sept 2021
Event23rd International Electronics Symposium, IES 2021 - Surabaya, Indonesia
Duration: 29 Sept 202130 Sept 2021

Publication series

NameInternational Electronics Symposium 2021: Wireless Technologies and Intelligent Systems for Better Human Lives, IES 2021 - Proceedings

Conference

Conference23rd International Electronics Symposium, IES 2021
Country/TerritoryIndonesia
CitySurabaya
Period29/09/2130/09/21

Keywords

  • Automatic Speech Recognition
  • Bayesian Optimization
  • BiLSTM-CNN
  • Hyperparameter Optimization
  • Random Forest

Fingerprint

Dive into the research topics of 'BiLSTM-CNN Hyperparameter Optimization for Speech Emotion and Stress Recognition'. Together they form a unique fingerprint.

Cite this