paper-with-me

홈 › Papers

Speech Disfluencies occur at Higher Perplexities

2020-12-01 · COLING (CogALex) 2020 12 · Priyanka Sen

Speech disfluencies have been hypothesized to occur before words that are less predictable and therefore more cognitively demanding. In this paper, we revisit this hypothesis by using OpenAI’s GPT-2 to calculate predictability of words as language model perplexity. Using the Switchboard corpus, we find that 51% of disfluencies occur at the highest, second highest, or within one token of the highest perplexity, and this distribution is not random. We also show that disfluencies precede words with significantly higher perplexity than fluent contexts. Based on our results, we offer new evidence that disfluencies are more likely to occur before less predictable words.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Semantic Parsing of Disfluent Speech

2021-04-01 · EACL 2021 2 · Priyanka Sen, Isabel Groves

Speech disfluencies are prevalent in spontaneous speech. The rising popularity of voice assistants presents a growing need to handle naturally occurring disfluencies. Semantic parsing is a key component for understanding…

Semantic Parsing

Expectation and Locality Effects in the Prediction of Disfluent Fillers and Repairs in English Speech

2019-06-01 · NAACL 2019 6 · Samvit Dammalapati, Rajakrishnan Rajkumar, Sumeet Agarwal

This study examines the role of three influential theories of language processing, \textit{viz.}, Surprisal Theory, Uniform Information Density (UID) hypothesis and Dependency Locality Theory (DLT), in predicting disflue…

Augmenting Automatic Speech Recognition Models with Disfluency Detection

2024-09-16 · Robin Amann, Zhaolin Li, Barbara Bruno, Jan Niehues

Speech disfluency commonly occurs in conversational and spontaneous speech. However, standard Automatic Speech Recognition (ASR) models struggle to accurately recognize these disfluencies because they are typically train…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Adversarial Training For Low-Resource Disfluency Correction

2023-06-10 · Vineet Bhat, Preethi Jyothi, Pushpak Bhattacharyya

Disfluencies commonly occur in conversational speech. Speech with disfluencies can result in noisy Automatic Speech Recognition (ASR) transcripts, which affects downstream tasks like machine translation. In this paper, w…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+1

Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectives

2023-01-25 · Tanvi Dinkar, Chloé Clavel, Ioana Vasilescu

Disfluencies (i.e. interruptions in the regular flow of speech), are ubiquitous to spoken discourse. Fillers ("uh", "um") are disfluencies that occur the most frequently compared to other kinds of disfluencies. Yet, to t…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1