Related papers: Cross-Language Speaker Attribute Prediction Using …
We present mSLAM, a multilingual Speech and LAnguage Model that learns cross-lingual cross-modal representations of speech and text by pre-training jointly on large amounts of unlabeled speech and text in multiple languages. mSLAM combines…
Cross-lingual transfer learning from high-resource to medium and low-resource languages has shown encouraging results. However, the scarcity of resources in target languages remains a challenge. In this work, we resort to data augmentation…
Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge sharing is usually achieved by using common lower-level layers for different…
This paper shows that pretraining multilingual language models at scale leads to significant performance gains for a wide range of cross-lingual transfer tasks. We train a Transformer-based masked language model on one hundred languages,…
In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch between labeled source domain data ("standard" accent) and unlabeled target domain…
Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…
Pre-trained Transformer-based speech models have shown striking performance when fine-tuned on various downstream tasks such as automatic speech recognition and spoken language identification (SLID). However, the problem of domain mismatch…
This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…
Pre-trained multilingual language models such as mBERT have shown immense gains for several natural language processing (NLP) tasks, especially in the zero-shot cross-lingual setting. Most, if not all, of these pre-trained models rely on…
Domain generalization remains a critical problem for speaker recognition, even with the state-of-the-art architectures based on deep neural nets. For example, a model trained on reading speech may largely fail when applied to scenarios of…
Large language models (LLMs) are very proficient text generators. We leverage this capability of LLMs to generate task-specific data via zero-shot prompting and promote cross-lingual transfer for low-resource target languages. Given…
The effects of language mismatch impact speech anti-spoofing systems, while investigations and quantification of these effects remain limited. Existing anti-spoofing datasets are mainly in English, and the high cost of acquiring…
Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…
Local dialects influence people to pronounce words of the same language differently from each other. The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic…
Accents mismatching is a critical problem for end-to-end ASR. This paper aims to address this problem by building an accent-robust RNN-T system with domain adversarial training (DAT). We unveil the magic behind DAT and provide, for the…
This paper contains a post-challenge performance analysis on cross-lingual speaker verification of the IDLab submission to the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). We show that current speaker embedding extractors…
Open domain dialog systems face the challenge of being repetitive and producing generic responses. In this paper, we demonstrate that by conditioning the response generation on interpretable discrete dialog attributes and composed…
In real-life applications, the performance of speaker recognition systems always degrades when there is a mismatch between training and evaluation data. Many domain adaptation methods have been successfully used for eliminating the domain…
Cross-lingual transfer (XLT) is an emergent ability of multilingual language models that preserves their performance on a task to a significant extent when evaluated in languages that were not included in the fine-tuning process. While…
The linguistic capabilities of Multimodal Large Language Models (MLLMs) are critical for their effective application across diverse tasks. This study aims to evaluate the performance of MLLMs on the VALSE benchmark, focusing on the efficacy…