相关论文: Voxlect: A Speech Foundation Model Benchmark for M…

For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various…

As language models are often deployed as chatbot assistants, it becomes a virtue for models to engage in conversations in a user's first language. While these models are trained on a wide range of languages, a comprehensive evaluation of…

Speech language models have recently demonstrated great potential as universal speech processing systems. Such models have the ability to model the rich acoustic information existing in audio signals, beyond spoken content, such as emotion,…

In recent years, the enhanced capabilities of ASR models and the emergence of multi-dialect datasets have increasingly pushed Arabic ASR model development toward an all-dialect-in-one direction. This trend highlights the need for…

Arabic is a complex language with many varieties and dialects spoken by over 450 millions all around the world. Due to the linguistic diversity and variations, it is challenging to build a robust and generalized ASR system for Arabic. In…

The pre-trained language model is trained on large-scale unlabeled text and can achieve state-of-the-art results in many different downstream tasks. However, the current pre-trained language model is mainly concentrated in the Chinese and…

We introduce XTREME-S, a new benchmark to evaluate universal cross-lingual speech representations in many languages. XTREME-S covers four task families: speech recognition, classification, speech-to-text translation and retrieval. Covering…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

Full-duplex voice agents--systems that listen and speak simultaneously--are rapidly moving from research to production. However, existing evaluations address conversational dynamics and task completion in isolation. We introduce…

This technical report describes the MERaLiON-SpeechEncoder, a foundation model designed to support a wide range of downstream speech applications. Developed as part of Singapore's National Multimodal Large Language Model Programme, the…

Vision-Language Foundation Models (VLMs), trained on large-scale multimodal datasets, have driven significant advances in Artificial Intelligence (AI) by enabling rich cross-modal reasoning. Despite their success in general domains,…

Investigating linguistic relationships on a global scale requires analyzing diverse features such as syntax, phonology and prosody, which evolve at varying rates influenced by internal diversification, language contact, and sociolinguistic…

For sensible progress in natural language processing, it is important that we are aware of the limitations of the evaluation metrics we use. In this work, we evaluate how robust metrics are to non-standardized dialects, i.e. spelling…

Large language models have shown strong performance on broad-domain knowledge and reasoning benchmarks, but it remains unclear how well language models handle specialized animal-related knowledge under a unified closed-book evaluation…

This work presents BanglaNLG, a comprehensive benchmark for evaluating natural language generation (NLG) models in Bangla, a widely spoken yet low-resource language. We aggregate six challenging conditional text generation tasks under the…

Word embeddings are a core component of modern natural language processing systems, making the ability to thoroughly evaluate them a vital task. We describe DiaLex, a benchmark for intrinsic evaluation of dialectal Arabic word embedding.…

We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis. Specifically, we extend VALL-E and train a multi-lingual conditional codec language model to predict the acoustic token sequences of the…

This paper introduces a new corpus of Mandarin-English code-switching speech recognition--TALCS corpus, suitable for training and evaluating code-switching speech recognition systems. TALCS corpus is derived from real online one-to-one…

Real-time speech assistants are becoming increasingly popular for ensuring improved accessibility to information. Bengali, being a low-resource language with a high regional dialectal diversity, has seen limited progress in developing such…

Conventional research on speech recognition modeling relies on the canonical form for most low-resource languages while automatic speech recognition (ASR) for regional dialects is treated as a fine-tuning task. To investigate the effects of…