logo Idiap Research Institute        
 [BibTeX] [Marc21]
Cross-transfer Knowledge between Speech and Text Encoders to Evaluate Customer Satisfaction
Type of publication: Conference paper
Citation: Parra-Gallego_INTERSPEECH_2024
Publication status: Accepted
Booktitle: Interspeech
Year: 2024
Month: September
Publisher: ISCA
Location: Kos Island, Greece
Abstract: Customer Satisfaction (CS) in call centers influences customer loyalty and the company's reputation. Traditionally, CS evaluations were conducted manually or with classical machine learning algorithms; however, advancements in deep learning have led to automated systems that evaluate CS using speech and text analyses. Previous studies have shown the text approach to be more accurate but relies on an external ASR for transcription. This study introduces a cross-transfer knowledge technique, distilling knowledge from the BERT model into speech encoders like Wav2Vec2, WavLM, and Whisper. By enriching these encoders with BERT’s linguistic information, we improve speech analysis performance and eliminate the need for an ASR. In evaluations on a dataset of customer opinions, our methods achieve over 92% accuracy in identifying CS categories, providing a faster and cost-effective solution compared to traditional text approaches.
Keywords: cross-transfer knowledge, Customer satisfaction, Spoken Language Understanding
Projects EMIL
Authors Parra-Gallego, Luis Felipe
Purohit, Tilak
Vlasenko, Bogdan
Orozco-Arroyave, Juan Rafael
Magimai.-Doss, Mathew
Added by: [UNK]
Total mark: 0
  • Parra-Gallego_INTERSPEECH_2024.pdf