相关论文: Cross-Language Speaker Attribute Prediction Using …

Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by…

Automatic Speech Recognition (ASR) models demonstrate outstanding performance on high-resource languages but face significant challenges when applied to low-resource languages due to limited training data and insufficient cross-lingual…

Domain adaptation faces a fundamental paradox in the cold-start regime. When target data is scarce, statistical methods fail to distinguish relevant source domains from irrelevant ones, which often leads to negative transfer. In this paper,…

Recent improvements in multilingual ASR have not been equally distributed across languages and language varieties. To advance state-of-the-art (SOTA) ASR models, we present the Interspeech 2025 ML-SUPERB 2.0 Challenge. We construct a new…

Multilingual Neural Machine Translation (MNMT) for low-resource languages (LRL) can be enhanced by the presence of related high-resource languages (HRL), but the relatedness of HRL usually relies on predefined linguistic assumptions about…

Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significant burden on token representations to encode all…

Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…

This paper proposes an improved approach for open-set speaker identification based on pretrained speaker foundation models. Building upon the previous Speaker Reciprocal Points Learning framework (V1), we first introduce an enhanced…

Transformer-based language models have achieved remarkable success in few-shot in-context learning and drawn a lot of research interest. However, these models' performance greatly depends on the choice of the example prompts and also has…

Multi-lingual contextualized embeddings, such as multilingual-BERT (mBERT), have shown success in a variety of zero-shot cross-lingual tasks. However, these models are limited by having inconsistent contextualized representations of…

Speech emotion recognition (SER) has attracted great attention in recent years due to the high demand for emotionally intelligent speech interfaces. Deriving speaker-invariant representations for speech emotion recognition is crucial. In…

Prompt-based methods leverage the knowledge of pre-trained language models (PLMs) trained with a masked language modeling (MLM) objective; however, these methods are sensitive to template, verbalizer, and few-shot instance selection,…

Multi-lingual language models (LM), such as mBERT, XLM-R, mT5, mBART, have been remarkably successful in enabling natural language tasks in low-resource languages through cross-lingual transfer from high-resource ones. In this work, we try…

Multilingual Language Models (\MLLMs) such as mBERT, XLM, XLM-R, \textit{etc.} have emerged as a viable option for bringing the power of pretraining to a large number of languages. Given their success in zero-shot transfer learning, there…

Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual…

Static and contextual multilingual embeddings have complementary strengths. Static embeddings, while less expressive than contextual language models, can be more straightforwardly aligned across multiple languages. We combine the strengths…

Self-supervised learning (SSL) in the pretraining stage using un-annotated speech data has been successful in low-resource automatic speech recognition (ASR) tasks. However, models trained through SSL are biased to the pretraining data…

Aspect-based sentiment analysis (ABSA) has received substantial attention in English, yet challenges remain for low-resource languages due to the scarcity of labelled data. Current cross-lingual ABSA approaches often rely on external…

The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability…

Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yielding a more useful general language model. Hence, we are…