mlsanityData to 13 Oct 2026

Domain Adapting Deep Reinforcement Learning for Real-world Speech Emotion Recognition

arXiv 2207.12248 ↗First posted 7 Jul 2022cs.SD cs.LG eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Computers can understand and then engage with people in an emotionally intelligent way thanks to speech-emotion recognition (SER). However, the performance of SER in cross-corpus and real-world live data feed scenarios can be significantly improved. The inability to adapt an existing model to a new domain is one of the shortcomings of SER methods. To address this challenge, researchers have developed domain adaptation techniques that transfer knowledge learnt by a model across the domain. Although existing domain adaptation techniques have improved performances across domains, they can be improved to adapt to a real-world live data feed situation where a model can self-tune while deployed. In this paper, we present a deep reinforcement learning-based strategy (RL-DA) for adapting a pre-trained model to a real-world live data feed setting while interacting with the environment and collecting continual feedback. RL-DA is evaluated on SER tasks, including cross-corpus and cross-language domain adaption schema. Evaluation results show that in a live data feed setting, RL-DA outperforms a baseline strategy by 11% and 14% in cross-corpus and cross-language scenarios, respectively.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 25 of its 87 references that are in the map. First posted on arXiv 7 Jul 2022.

Builds on

25 of 87 references.

References · 25

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,870
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,221
  3. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 662
  4. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
  5. 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 325
  6. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 279
  7. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 259
  8. 2021Emotional Voice Conversion: Theory, Databases and ESDcited by 114
  9. 2019Meta Reinforcement Learning for Sim-to-real Domain Adaptationcited by 49
  10. 2020Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trendscited by 28
  11. 2020Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognitioncited by 21
  12. 2019Improving Cross-Corpus Speech Emotion Recognition with Adversarial Discriminative Domain Generalization (ADDoG)cited by 19
13 more
  1. 2021A Survey on Deep Reinforcement Learning for Audio-Based Applicationscited by 17
  2. 2013Feature Learning in Deep Neural Networks - Studies on Speech Recognition Taskscited by 14
  3. 2019Direct Modelling of Speech Emotion from Raw Speechcited by 13
  4. 2019Unsupervised Adversarial Domain Adaptation for Cross-Lingual Speech Emotion Recognitioncited by 10
  5. 2021Unsupervised Domain Adaptation Schemes for Building ASR in Low-resource Languagescited by 9
  6. 2022A cross-corpus study on speech emotion recognitioncited by 7
  7. 2021Emotion Recognition for Healthcare Surveillance Systems Using Neural Networks: A Surveycited by 6
  8. 2018Domain Adaptation for Reinforcement Learning on the Ataricited by 5
  9. 2018EmoRL: Continuous Acoustic Emotion Classification using Deep Reinforcement Learningcited by 4
  10. 2019Pre-training in Deep Reinforcement Learning for Automatic Speech Recognitioncited by 3
  11. 2020Deep Reinforcement Learning with Pre-training for Time-efficient Training of Automatic Speech Recognitioncited by 3
  12. 2021A novel policy for pre-trained Deep Reinforcement Learning for Speech Emotion Recognitioncited by 2
  13. 2019Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognitioncited by 1

Built on by

Not cited yet.