paper-with-me

홈 › Papers

The importance of fillers for text representations of speech transcripts

2020-09-23 · EMNLP 2020 11 · Tanvi Dinkar, Pierre Colombo, Matthieu Labeau, Chloé Clavel

While being an essential component of spoken language, fillers (e.g."um" or "uh") often remain overlooked in Spoken Language Understanding (SLU) tasks. We explore the possibility of representing them with deep contextualised embeddings, showing improvements on modelling spoken language and two downstream tasks - predicting a speaker's stance and expressed confidence.

📄 PDF Abstract BibTeX arXiv:2009.11340

Code (0)

등록된 구현이 없습니다.

Tasks

Spoken Language Understanding

Similar Papers 제목 키워드 기반

Evaluating Sampling-based Filler Insertion with Spontaneous TTS

2022-06-01 · LREC 2022 6 · Siyang Wang, Joakim Gustafson, Éva Székely

Inserting fillers (such as “um”, “like”) to clean speech text has a rich history of study. One major application is to make dialogue systems sound more spontaneous. The ambiguity of filler occurrence and inter-speaker di…

Importance-related Fillers Improve the Classification Accuracy of the Response Time Concealed Information Test in a Crime Scenario

2021-05-01 · Jerzy Wojciechowski, Gáspár Lukács

Purpose. The Response Time Concealed Information Test (RT-CIT) can reveal when a person recognizes a relevant item among other irrelevant items, based on comparatively slower responding. Therefore, if a person is conceal…

DiagnosticOpen-Ended Question Answering

ComedicSpeech: Text To Speech For Stand-up Comedies in Low-Resource Scenarios

2023-05-20 · Yuyue Wang, Huan Xiao, Yihan Wu, Ruihua Song

Text to Speech (TTS) models can generate natural and high-quality speech, but it is not expressive enough when synthesizing speech with dramatic expressiveness, such as stand-up comedies. Considering comedians have diver…

Rhythmtext-to-speechText to Speech

Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs

2026-05-12 · Deepak Kumar, Baban Gain, Asif Ekbal arxiv

Automatic Speech Recognition (ASR) transcripts often contain disfluencies, such as fillers, repetitions, and false starts, which reduce readability and hinder downstream applications like chatbots and voice assistants. I…

Contrastive LearningSpeech RecognitionData Augmentation

Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?

2021-11-29 · Lasse Borgholt, Jakob Drachmann Havtorn, Mostafa Abdou, Joakim Edin 외

Spoken language understanding (SLU) tasks are usually solved by first transcribing an utterance with automatic speech recognition (ASR) and then feeding the output to a text-based model. Recent advances in self-supervise…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationnamed-entity-recognition+7