AlloSat: A New Call Center French Corpus for Satisfaction and Frustration Analysis
We present a new corpus, named AlloSat, composed of real-life call center conversations in French that is continuously annotated in frustration and satisfaction. This corpus has been set up to develop new systems able to model the continuous aspect of semantic and paralinguistic information at the conversation level. The present work focuses on the paralinguistic level, more precisely on the expression of emotions. In the call center industry, the conversation usually aims at solving the caller{'}s request. As far as we know, most emotional databases contain static annotations in discrete categories or in dimensions such as activation or valence. We hypothesize that these dimensions are not task-related enough. Moreover, static annotations do not enable to explore the temporal evolution of emotional states. To solve this issue, we propose a corpus with a rich annotation scheme enabling a real-time investigation of the axis frustration / satisfaction. AlloSat regroups 303 conversations with a total of approximately 37 hours of audio, all recorded in real-life environments collected by Allo-Media (an intelligent call tracking company). First regression experiments, with audio features, show that the evolution of frustration / satisfaction axis can be retrieved automatically at the conversation level.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Pr\'ediction continue de la satisfaction et de la frustration dans des conversations de centre d'appels (AlloSat : A New Call Center French Corpus for Affect Analysis)
Nous pr{\'e}sentons un nouveau corpus, nomm{\'e} AlloSat, compos{\'e} de conversations en fran{\c{c}}ais extraites de centre d{'}appels, annot{\'e}es de fa{\c{c}}on continue en frustration et satisfaction. Dans le contex…
On the use of Self-supervised Pre-trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition
Pre-training for feature extraction is an increasingly studied approach to get better continuous representations of audio and text content. In the present work, we use wav2vec and camemBERT as self-supervised learned mod…
Emotion RecognitionSpeech Emotion RecognitionAcoustic and linguistic representations for speech continuous emotion recognition in call center conversations
The goal of our research is to automatically retrieve the satisfaction and the frustration in real-life call-center conversations. This study focuses an industrial application in which the customer satisfaction is contin…
Emotion RecognitionTransfer LearningEvaluation automatique de la satisfaction client \`a partir de conversations de type ``chat'' par r\'eseaux de neurones r\'ecurrents avec m\'ecanisme d'attention (Customer satisfaction prediction with attention-based RNNs from a chat contact center corpus)
Cet article pr{\'e}sente des m{\'e}thodes permettant l{'}{\'e}valuation de la satisfaction client {\`a} partir de tr{\`e}s vastes corpus de conversation de type {``}chat{''} entre des clients et des op{\'e}rateurs. Extra…
Syntactic annotation of spontaneous speech: application to call-center conversation data
This paper describes the syntactic annotation process of the DECODA corpus. This corpus contains manual transcriptions of spoken conversations recorded in the French call-center of the Paris Public Transport Authority (R…
Dependency ParsingPOSSpeech RecognitionSpoken Language Understanding