Mitigating the Impact of Speech Recognition Errors on Chatbot using Sequence-to-Sequence Model

2017/09/22 by Pin-Jung Chen, Chen, Pin-Jung, I-Hung Hsu +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1709.07862

openalex publication_date 2017/09/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We apply sequence-to-sequence model to mitigate the impact of speech recognition errors on open domain end-to-end dialog generation. We cast the task as a domain adaptation problem where ASR transcriptions and original text are in two different domains. In this paper, our proposed model includes two individual encoders for each domain data and make their hidden states similar to ensure the decoder predict the same dialog text. The method shows that the sequence-to-sequence model can learn the ASR transcriptions and original text pair having the same meaning and eliminate the speech recognition errors. Experimental results on Cornell movie dialog dataset demonstrate that the domain adaption system help the spoken dialog system generate more similar responses with the original text answers.

Citations

• Adam: A Method for Stochastic Optimization
• Deep Domain Confusion: Maximizing for Domain Invariance
• Adversarial Discriminative Domain Adaptation

Related

• Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study
• Hallucination of speech recognition errors with sequence to sequence\n learning
• Unsupervised domain adaptation for speech recognition with unsupervised error correction
• ASR Error Correction using Large Language Models
• Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correction