Open-source conversational ai with speechbrain 1.0

M Ravanelli, T Parcollet, A Moumen… - Journal of Machine …, 2024 - jmlr.org
SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused
particularly on speech processing tasks such as speech recognition, speech enhancement …

Progres: Prompted generative rescoring on asr n-best

AD Tur, A Moumen, M Ravanelli - 2024 IEEE Spoken …, 2024 - ieeexplore.ieee.org
Large Language Models (LLMs) have shown their ability to improve the performance of
speech recognizers by effectively rescoring the n-best hypotheses generated during the …

Comparing Pre-Trained Embeddings and Domain-Independent Features for Regression-Based Evaluation of Task-Oriented Dialogue Systems

K Georgila - Proceedings of the 25th Annual Meeting of the …, 2024 - aclanthology.org
Abstract We use Gaussian Process Regression to predict different types of ratings provided
by users after interacting with various task-oriented dialogue systems. We compare the …

Speechworthy instruction-tuned language models

H Cho, N Jedema, LFR Ribeiro, K Sharma… - arxiv preprint arxiv …, 2024 - arxiv.org
Current instruction-tuned language models are exclusively trained with textual preference
data and thus are often not aligned with the unique requirements of other modalities, such …

E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models

Z Zhang, B Hao, J Li, Z Zhang, D Zhao - arxiv preprint arxiv:2406.10950, 2024 - arxiv.org
Most large language models (LLMs) are sensitive to prompts, and another synonymous
expression or a typo may lead to unexpected results for the model. Composing an optimal …