Papers by Marie Tahon
Automatic Speech Interruption Detection: Analysis, Corpus, and System (2024.lrec-main)
Copied to clipboard
| Challenge: | Interruption detection is a new but challenging task in the field of speech processing. |
| Approach: | They propose to define automatic speech interruption detection and build a specialized corpus to analyze interrupted conversations. |
| Outcome: | The proposed system can detect interruptions in speech with promising results . it can be used to ensure speaking turns are respected during official political debates . |
ALLIES: A Speech Corpus for Segmentation, Speaker Diarization, Speech Recognition and Speaker Change Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | a meta corpus of audio files is used to gather, annotate and transcribe speech . a large number of speech databases are needed to perform multi-speaker tasks such as speaker diarization and speaker change detection. |
| Approach: | They propose to use human feedback to homogenize and correct speaker labels among the audio files by integrating human feedback within a speaker verification system. |
| Outcome: | The proposed protocol evaluates speech segmentation, speaker diarization, speech transcription and speaker change detection using human feedback. |
AlloSat: A New Call Center French Corpus for Satisfaction and Frustration Analysis (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing systems retrieve emotional information from textual transcriptions or from audio signal. |
| Approach: | They propose to use a call center corpus that is continuously annotated in frustration and satisfaction to model the continuous aspect of semantic and paralinguistic information at the conversation level. |
| Outcome: | The proposed system can model the paralinguistic aspect of semantic and paralinguistic information at the conversation level. |
SynPaFlex-Corpus: An Expressive French Audiobooks Corpus dedicated to expressive speech synthesis. (L18-1)
Copied to clipboard
| Challenge: | a French audiobooks corpus contains 87 hours of good audio quality speech . audiobooks provide mono-genre and multi-speaker speech whereas audiobooks usually provide a few hours of mono- and multispeakers . |
| Approach: | They present an expressive French audiobooks corpus containing eighty seven hours of speech . the corpus is annotated automatically and provides information as phone labels, phone boundaries, syllables, words or morpho-syntactic tagging. |
| Outcome: | The proposed corpus contains 87 hours of speech recorded by a single speaker . the data will allow developing models to better control expressiveness in speech synthesis . |
Overlaps and Gender Analysis in the Context of Broadcast Media (2022.lrec-1)
Copied to clipboard
| Challenge: | Using gender and overlap annotations, we characterise interactions between speakers according to their gender and role in broadcast media. |
| Approach: | They propose to characterise interactions between speakers according to their gender and role in broadcast media by using a small dataset of 93 recordings from LCP French channel. |
| Outcome: | The proposed method could improve the efficiency of qualitative studies conducted in human sciences. |
Towards Interactive Annotation for Hesitation in Conversational Speech (2020.lrec-1)
Copied to clipboard
| Challenge: | recognizing affects in spontaneous, non acted speech is expensive in both human resources and time. |
| Approach: | They aim to automatize the labeling of hesitant speech as a marker of expressed uncertainty. |
| Outcome: | The proposed method shows that the number of filled pauses and vowel duration increases with the degree of hesitation, and that automatic prediction of the hesitation degree reaches encouraging RMSE results of 1.6. |
A Semi-Automatic Approach to Create Large Gender- and Age-Balanced Speaker Corpora: Usefulness of Speaker Diarization & Identification. (2022.lrec-1)
Copied to clipboard
Rémi Uro, David Doukhan, Albert Rilliard, Laetitia Larcher, Anissa-Claire Adgharouamane, Marie Tahon, Antoine Laurent
| Challenge: | Existing methods for creating diachronic corpus of voices are based on speaker characteristics and require human intervention. |
| Approach: | They propose to use a semi-automatic pipeline to create a diachronic corpus of voices balanced for speaker’s age, gender and recording period, according to 32 categories. |
| Outcome: | The proposed method cut down on manual annotations by ten and provides high quality speech for most of the selected excerpts. |
Annotation of Transition-Relevance Places and Interruptions for the Description of Turn-Taking in Conversations in French Media Content (2024.lrec-main)
Copied to clipboard
| Challenge: | Few speech resources describe interruption phenomena, especially for TV and media content. |
| Approach: | They propose to annotation Transition-Relevance Places (TRPs) and Floor-Taking event types on an existing French TV and Radio broadcast corpus to facilitate studies of interruptions and turn-taking. |
| Outcome: | The proposed annotations on an existing French TV and Radio broadcast corpus show they are reliable and reliable . |