Related papers: Improved Language Identification Through Cross-Lin…
Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies under the pre-training framework, however, remain…
Recent models such as XLS-R and Whisper have made multilingual speech technologies more accessible by pre-training on audio from around 100 spoken languages each. However, there are thousands of spoken languages worldwide, and adapting to…
Self-supervision has shown great potential for audio-visual speech recognition by vastly reducing the amount of labeled data required to build good systems. However, existing methods are either not entirely end-to-end or do not train joint…
We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict the masked speech signals, in the form of discrete labels generated with a random-projection quantizer. In…
Recent studies have shown how self-supervised models can produce accurate speech quality predictions. Speech representations generated by the pre-trained wav2vec 2.0 model allows constructing robust predicting models using small amounts of…
Spoken language recognition (SLR) is the task of automatically identifying the language present in a speech signal. Existing SLR models are either too computationally expensive or too large to run effectively on devices with limited…
In this paper, we improve speech translation (ST) through effectively leveraging large quantities of unlabeled speech and text data in different and complementary ways. We explore both pretraining and self-training by using the large…
End-to-end speech-to-text translation can provide a simpler and smaller system but is facing the challenge of data scarcity. Pre-training methods can leverage unlabeled data and have been shown to be effective on data-scarce settings. In…
We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech…
In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…
The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task.…
Self-supervised learning has emerged as a powerful approach for leveraging large-scale unlabeled data to improve model performance in various domains. In this paper, we explore masked self-supervised pre-training for text recognition…
Recent advancements in Deep and Self-Supervised Learning (SSL) have led to substantial improvements in Speech Emotion Recognition (SER) performance, reaching unprecedented levels. However, obtaining sufficient amounts of accurately labeled…
Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques which may provide…
This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise…
In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training…
Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in…
Emotion recognition is a challenging task due to limited availability of in-the-wild labeled datasets. Self-supervised learning has shown improvements on tasks with limited labeled datasets in domains like speech and natural language.…
Recently, self-supervised pre-training has shown significant improvements in many areas of machine learning, including speech and NLP. We propose using large self-supervised pre-trained models for both audio and text modality with…
Recent advances in self-supervised learning through contrastive training have shown that it is possible to learn a competitive speech recognition system with as little as 10 minutes of labeled data. However, these systems are…