Abstract book: https://www.isca-archive.org/interspeech_2025/booklet.pdf /// Full conference proceedings: https://www.isca-archive.org/interspeech_2025/

International audience

Typical foreign language (L2) pronunciation training focuses mainly on individual sounds. Intonation, the patterns of pitch change across words or phrases is often neglected, despite its key role in word-level intelligibility and in the expression of attitudes and affect. This paper examines hand-controlled real-time vocal synthesis, known as Performative Vocal Synthesis (PVS), as an interaction technique for practicing L2 intonation in computer aided pronunciation training (CAPT).

International audience

International audience

Altered quality of the phonetic-acoustic information in the speech signal in the case of motor speech disorders may reduce its intelligibility. Monitoring intelligibility is part of the standard clinical assessment of patients. It is also a valuable tool to index the evolution of the speech disorder. However, measuring intelligibility raises methodological debates concerning: the type of linguistic material on which the assessment is based (non-words, words, continuous speech), the evaluation protocol and type of scores (scale-based rating, transcription or recognition tests), and the advantages and disadvantages of listener vs. automatic-based approaches (subjective vs. objective, expertise level, types of models used). In this paper, the intelligibility of the speech of 32 French patients presenting mild to moderate dysarthria and 17 elderly speakers is assessed with five different methods: impressionistic clinician judgment on continuous speech, number of words recognized in an interactive face-to-face setting and in an on-line testing of the same material by 75 judges, automatic feature-based and automatic speech recognition-based methods (both on short sentences). The implications of the different methods for clinical practice are discussed.

Our knowledge on speech is historically built on data comparing different speakers or data averaged across speakers. Consequently, little is known on the variability in the speech of a single individual. Experimental studies have shown that speakers adapt to the linguistic and the speaking contexts, and modify their speech according to their emotional or biological condition, etc. However, it is unclear how much speakers vary from one repetition to the next, and how comparable are recordings that are collected days, months or years apart. In this paper, we introduce two French databases which contain recordings of 9 to 11 speakers recorded over 9 to 18 sessions, allowing comparisons of speech tasks with a different delay between the repetitions: 3 repetitions within the same session, 6 to 10 repetitions on different days during a two months period, 5 to 9 repetitions on different years. Speakers are recorded on a large set of speech tasks including read and spontaneous speech as well as speech-like performance tasks. In this paper, we provide detailed descriptions of the two databases and available annotations. We conclude by an illustration on how these data can inform on within-speaker variability of speech.

International audience

Manual annotation of speech corpora is expensive in both human resources and time. Furthermore, recognizing affects in spontaneous, non acted speech presents a challenge for humans and machines. The aim of the present study is to automatize the labeling of hesitant speech as a marker of expressed uncertainty. That is why, the NCCFr-corpus was manually annotated for ‘degree of hesitation’ on a continuous scale between -3 and 3 and the affective dimensions ‘activation, valence and control’. In total, 5834 chunks of the NCCFr-corpus were manually annotated. Acoustic analyses were carried out based on these annotations. Furthermore, regression models were trained in order to allow automatic prediction of hesitation for speech chunks that do not have a manual annotation. Preliminary results show that the number of filled pauses as well as vowel duration increase with the degree of hesitation, and that automatic prediction of the hesitation degree reaches encouraging RMSE results of 1.6.

International audience

International audience

International audience

International audience

This paper describes the participation of the LIA in the Human Assisted Speaker Recognition (HASR) task of the NIST-SRE 2010 evaluation campaign and its extension to a larger number of listeners.The human performance in such unfavorable conditions is analyzed in relation to the decision of a speaker recognition automatic system. Results of the perception test showed an important inter-trial variability (from 3% to 90% of correct answers for non-target trials) whereas there was no significant difference between the experienced and inexperienced listeners. Some complementarity between speaker verification system and human decisions was also found.

International audience

International audience