Findings of the IWSLT 2022 Evaluation Campaign.
The evaluation campaign of the 19th International Conference on Spoken Language
Translation featured eight shared tasks:(i) Simultaneous speech translation,(ii) Offline …
Translation featured eight shared tasks:(i) Simultaneous speech translation,(ii) Offline …
LeBenchmark 2.0: A standardized, replicable and enhanced framework for self-supervised representations of French speech
Self-supervised learning (SSL) is at the origin of unprecedented improvements in many
different domains including computer vision and natural language processing. Speech …
different domains including computer vision and natural language processing. Speech …
Probing sentiment-oriented pre-training inspired by human sentiment perception mechanism
T Feng, J Liu, J Yang - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Pre-training of deep convolutional neural networks (DCNNs) plays a crucial role in the field
of visual sentiment analysis (VSA). Most proposed methods employ the off-the-shelf …
of visual sentiment analysis (VSA). Most proposed methods employ the off-the-shelf …
Xtreme-s: Evaluating cross-lingual speech representations
We introduce XTREME-S, a new benchmark to evaluate universal cross-lingual speech
representations in many languages. XTREME-S covers four task families: speech …
representations in many languages. XTREME-S covers four task families: speech …
Exploring capabilities of monolingual audio transformers using large datasets in automatic speech recognition of Czech
In this paper, we present our progress in pretraining Czech monolingual audio transformers
from a large dataset containing more than 80 thousand hours of unlabeled speech, and …
from a large dataset containing more than 80 thousand hours of unlabeled speech, and …
A study of gender impact in self-supervised models for speech-to-text systems
Self-supervised models for speech processing emerged recently as popular foundation
blocks in speech processing pipelines. These models are pre-trained on unlabeled audio …
blocks in speech processing pipelines. These models are pre-trained on unlabeled audio …
ON-TRAC consortium systems for the IWSLT 2022 dialect and low-resource speech translation tasks
This paper describes the ON-TRAC Consortium translation systems developed for two
challenge tracks featured in the Evaluation Campaign of IWSLT 2022: low-resource and …
challenge tracks featured in the Evaluation Campaign of IWSLT 2022: low-resource and …
Speech resources in the tamasheq language
In this paper we present two datasets for Tamasheq, a developing language mainly spoken
in Mali and Niger. These two datasets were made available for the IWSLT 2022 low …
in Mali and Niger. These two datasets were made available for the IWSLT 2022 low …
Cross-domain voice activity detection with self-supervised representations
Voice Activity Detection (VAD) aims at detecting speech segments on an audio signal, which
is a necessary first step for many today's speech based applications. Current state-of-the-art …
is a necessary first step for many today's speech based applications. Current state-of-the-art …
Hats: An open data set integrating human perception applied to the evaluation of automatic speech recognition metrics
Abstract Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on
their ability to correctly recognize each word contained in a speech signal. In this context, the …
their ability to correctly recognize each word contained in a speech signal. In this context, the …