Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition
In this paper, we present a method for correcting automatic speech recognition (ASR) errors using a finite state transducer (FST) intent recognition framework. Intent recognition is a powerful technique for dialog flow management in turn-oriented, human-machine dialogs. This technique can also be very useful in the context of human-human dialogs, though it serves a different purpose of key insight extraction from conversations. We argue that currently available intent recognition techniques are not applicable to human-human dialogs due to the complex structure of turn-taking and various disfluencies encountered in spontaneous conversations, exacerbated by speech recognition errors and scarcity of domain-specific labeled data. Without efficient key insight extraction techniques, raw human-human dialog transcripts remain significantly unexploited. Our contribution consists of a novel FST for intent indexing and an algorithm for fuzzy intent search over the lattice - a compact graph encoding of ASR's hypotheses. We also develop a pruning strategy to constrain the fuzziness of the FST index search. Extracted intents represent linguistic domain knowledge and help us improve (rescore) the original transcript. We compare our method with a baseline, which uses only the most likely transcript hypothesis (best path), and find an increase in the total number of recognized intents by 25%.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Intent RecognitionManagementspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
LVLMs are Bad at Overhearing Human Referential Communication
During spontaneous conversations, speakers collaborate on novel referring expressions, which they can then re-use in subsequent conversations. Understanding such referring expressions is an important ability for an embod…
Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?
Automatic Speech Recognition (ASR) systems introduce word errors, which often confuse punctuation prediction models, turning punctuation restoration into a challenging task. These errors usually take the form of homonyms…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)PredictionPunctuation Restoration+3Designing Spontaneous Speech Search Interface for Historical Archives
Spontaneous speech in the form of conversations, meetings, voice-mail, interviews, oral history, etc. is one of the most ubiquitous forms of human communication. Search engines providing access to such speech collections…
Are We NER Yet? Measuring the Impact of ASR Errors on Named Entity Recognition in Spontaneous Conversation Transcripts
Transcriptions of spontaneous human conversations present a significant obstacle for traditional NER models trained on prescriptive written language. The lack of grammatical structure of spoken utterances, combined with …
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERSpontaneous Persuasion: An Audit of Model Persuasiveness in Everyday Conversations
Large language models (LLMs) possess strong persuasive capabilities that outperform humans in head-to-head comparisons. Users report consulting LLMs to inform major life decisions in relationships, medical settings, and …