English
Related papers

Related papers: MLS: A Large-Scale Multilingual Dataset for Speech…

200 papers

Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks. However, their applicability is still less explored in low-resource…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-08 Seraphina Fong , Marco Matassoni , Alessio Brutti

Multimodal Large Language Models (MLLMs) have achieved great success in Speech-to-Text Translation (S2TT) tasks. However, current research is constrained by two key challenges: language coverage and efficiency. Most of the popular S2TT…

Computation and Language · Computer Science 2026-04-14 Yexing Du , Kaiyuan Liu , Youcheng Pan , Bo Yang , Keqi Deng , Xie Chen , Yang Xiang , Ming Liu , Bing Qin , YaoWei Wang

We present Belebele, a multiple-choice machine reading comprehension (MRC) dataset spanning 122 language variants. Significantly expanding the language coverage of natural language understanding (NLU) benchmarks, this dataset enables the…

Recent work suggests that large language models (LLMs) can improve performance of speech tasks compared to existing systems. To support their claims, results on LibriSpeech and Common Voice are often quoted. However, this work finds that a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-06 Yuan Tseng , Titouan Parcollet , Rogier van Dalen , Shucong Zhang , Sourav Bhattacharya

Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages behind. Expanding ASR coverage has been costly and limited by…

Self-supervised learning (SSL) models have achieved considerable improvements in automatic speech recognition (ASR). In addition, ASR performance could be further improved if the model is dedicated to audio content information learning…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-08 Genshun Wan , Tan Liu , Hang Chen , Jia Pan , Cong Liu , Zhongfu Ye

We release MMSMR, a Massively Multi-System MultiReference dataset to enable future work on metrics and evaluation for dialog. Automatic metrics for dialogue evaluation should be robust proxies for human judgments; however, the verification…

Computation and Language · Computer Science 2024-11-20 Huda Khayrallah , Zuhaib Akhtar , Edward Cohen , Jyothir S , João Sedoc

It is well known that many machine learning systems demonstrate bias towards specific groups of individuals. This problem has been studied extensively in the Facial Recognition area, but much less so in Automatic Speech Recognition (ASR).…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-22 Chunxi Liu , Michael Picheny , Leda Sarı , Pooja Chitkara , Alex Xiao , Xiaohui Zhang , Mark Chou , Andres Alvarado , Caner Hazirbas , Yatharth Saraf

This work presents a lifelong learning approach to train a multilingual Text-To-Speech (TTS) system, where each language was seen as an individual task and was learned sequentially and continually. It does not require pooled data from all…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-20 Mu Yang , Shaojin Ding , Tianlong Chen , Tong Wang , Zhangyang Wang

Recent advances in speech synthesis and voice conversion have greatly improved the naturalness and authenticity of generated audio. Meanwhile, evolving encoding, compression, and transmission mechanisms on social media platforms further…

Sound · Computer Science 2026-03-09 Daixian Li , Jun Xue , Yanzhen Ren , Zhuolin Yi , Yihuan Huang , Guanxiang Feng , Yi Chai

We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly…

Computation and Language · Computer Science 2016-11-01 Hagen Soltau , Hank Liao , Hasim Sak

Despite impressive advancements in multilingual corpora collection and model training, developing large-scale deployments of multilingual models still presents a significant challenge. This is particularly true for language tasks that are…

Computation and Language · Computer Science 2023-06-14 Łukasz Augustyniak , Szymon Woźniak , Marcin Gruza , Piotr Gramacki , Krzysztof Rajda , Mikołaj Morzy , Tomasz Kajdanowicz

We improve low-resource ASR by integrating the ideas of multilingual training and self-supervised learning. Concretely, we leverage an International Phonetic Alphabet (IPA) multilingual model to create frame-level pseudo labels for…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-22 Siyuan Feng , Ming Tu , Rui Xia , Chuanzeng Huang , Yuxuan Wang

High-resource languages such as English, enables the pretraining of high-quality large language models (LLMs). The same can not be said for most other languages as LLMs still underperform for non-English languages, likely due to a gap in…

Computation and Language · Computer Science 2025-02-20 Jiayi Wang , Yao Lu , Maurice Weber , Max Ryabinin , David Adelani , Yihong Chen , Raphael Tang , Pontus Stenetorp

Large Language Models (LLMs) are increasingly used in Spoken Language Understanding (SLU), where effective multimodal learning depends on the alignment between audio and text. Despite various fusion methods, no standard metric exists to…

Computation and Language · Computer Science 2025-07-08 Pooneh Mousavi , Yingzhi Wang , Mirco Ravanelli , Cem Subakan

We present an ongoing initiative to provide open, very large, high-quality, and richly annotated textual datasets for almost 200 languages. At 30 trillion tokens, this is likely the largest generally available multilingual collection of LLM…

Recent advancements in Large Language Models (LLMs) have significantly influenced the landscape of language and speech research. Despite this progress, these models lack specific benchmarking against state-of-the-art (SOTA) models tailored…

The political biases of Large Language Models (LLMs) are usually assessed by simulating their answers to English surveys. In this work, we propose an alternative framing of political biases, relying on principles of fairness in multilingual…

Computation and Language · Computer Science 2026-03-12 Paul Lerner , François Yvon

We present a corpus of sentence-aligned triples of German audio, German text, and English translation, based on German audiobooks. The speech translation data consist of 110 hours of audio material aligned to over 50k parallel sentences. An…

Computation and Language · Computer Science 2020-03-05 Benjamin Beilharz , Xin Sun , Sariya Karimova , Stefan Riezler