9 papers
An Ultra-Low Latency, End-to-End Streaming Speech Synthesis Architecture via Block-Wise Generation and Depth-Wise Codec Decoding
Tianhui Su, Tien-Ping Tan, Salima Mdhaffar +2
Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computa…
SLURP-TN : Resource for Tunisian Dialect Spoken Language Understanding
Haroun Elleuch, Salima Mdhaffar, Yannick Estève +1
Spoken Language Understanding (SLU) aims to extract the semantic information from the speech utterance of user queries. It is a core component in a task-oriented dialogue system. W…
Ara-Best-RQ: Multi Dialectal Arabic SSL
Haroun Elleuch, Ryan Whetten, Salima Mdhaffar +2
We present Ara-BEST-RQ, a family of self-supervised learning (SSL) models specifically designed for multi-dialectal Arabic speech processing. Leveraging 5,640 hours of crawled Crea…
Pantagruel: Unified Self-Supervised Encoders for French Text and Speech
Phuong-Hang Le, Valentin Pelloin, Arnault Chatelain +27
We release Pantagruel models, a new family of self-supervised encoder models for French text and speech. Instead of predicting modality-tailored targets such as textual tokens or s…
SENSE models: an open source solution for multilingual and multimodal semantic-based tasks
Salima Mdhaffar, Haroun Elleuch, Chaimae Chellaf +2
This paper introduces SENSE (Shared Embedding for N-lingual Speech and tExt), an open-source solution inspired by the SAMU-XLSR framework and conceptually similar to Meta AI's SONA…
TEDxTN: A Three-way Speech Translation Corpus for Code-Switched Tunisian Arabic - English
Fethi Bougares, Salima Mdhaffar, Haroun Elleuch +1
In this paper, we introduce TEDxTN, the first publicly available Tunisian Arabic to English speech translation dataset. This work is in line with the ongoing effort to mitigate the…