Miscommunication handling in spoken dialog systems based on error-aware dialog state detection
| Autor: | Ming-Hsiang Su, Wei-Bin Liang, Chung-Hsien Wu |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Acoustics and Ultrasonics
Computer science Speech recognition Semantic interpretation lcsh:QC221-246 02 engineering and technology computer.software_genre lcsh:QA75.5-76.95 Task (project management) 030507 speech-language pathology & audiology 03 medical and health sciences 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering Dialog system Dialog box business.industry Latent semantic analysis Error-aware dialog act Spoken dialog systems Miscommunication lcsh:Acoustics. Sound 020201 artificial intelligence & image processing lcsh:Electronic computers. Computer science Artificial intelligence 0305 other medical science business computer Sentence Natural language processing Utterance |
| Zdroj: | EURASIP Journal on Audio, Speech, and Music Processing, Vol 2017, Iss 1, Pp 1-17 (2017) |
| ISSN: | 1687-4722 |
| DOI: | 10.1186/s13636-017-0107-3 |
| Popis: | With the exponential growth in computing power and progress in speech recognition technology, spoken dialog systems (SDSs) with which a user interacts through natural speech has been widely used in human-computer interaction. However, error-prone automatic speech recognition (ASR) results usually lead to inappropriate semantic interpretation so that miscommunication happens easily. This paper presents an approach to error-aware dialog state (DS) detection for robust miscommunication handling in an SDS. Non-understanding (Non-U) and misunderstanding (Mis-U) are considered for miscommunication handling in this study. First, understanding evidence (UE), derived from the recognition confidence, is adopted for Non-U detection followed by Non-U recovery. For Mis-U with the recognized sentence containing uncertain recognized words, the partial sentences obtained by removing potentially misrecognized words from the input utterance are organized, based on regular expressions, as a tree structure to tolerate the deletion or rejection of keywords resulting from misrecognition for Mis-U DS modeling. Latent semantic analysis is then employed to consider the verified words and their n-grams for DS detection, including Mis-U and predefined Base DSs. Historical information-based n-grams are employed to find the most likely DS for the SDS. Several experiments were performed with a dialog corpus for the restaurant reservation task. The experimental results show that the proposed approach achieved a promising performance for Non-U recovery and Mis-U repair as well as a satisfactory task success rate for the dialogs using the proposed method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink