English
Related papers

Related papers: HeceTokenizer: A Syllable-Based Tokenization Appro…

200 papers

Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. These tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation.…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-12 Xuan Shi , Chang Zeng , Tiantian Feng , Shih-Heng Wang , Jianbo Ma , Shrikanth Narayanan

Audio-text retrieval is a challenging task, requiring the search for an audio clip or a text caption within a database. The predominant focus of existing research on English descriptions poses a limitation on the applicability of such…

Sound · Computer Science 2024-06-18 Zhiyong Yan , Heinrich Dinkel , Yongqing Wang , Jizhong Liu , Junbo Zhang , Yujun Wang , Bin Wang

Encoder-decoder models provide a generic architecture for sequence-to-sequence tasks such as speech recognition and translation. While offline systems are often evaluated on quality metrics like word error rates (WER) and BLEU, latency is…

Computation and Language · Computer Science 2020-10-14 Danni Liu , Gerasimos Spanakis , Jan Niehues

We propose an innovative token representation and update method in a new ultra-small language model: the Wave network. Specifically, we use a complex vector to represent each token, encoding both global and local semantics of the input…

Computation and Language · Computer Science 2024-11-12 Xin Zhang , Victor S. Sheng

Adapting language models to new data distributions by simple finetuning is challenging. This is due to the rigidity of their subword tokenizers, which typically remain unchanged during adaptation. This inflexibility often leads to…

Computation and Language · Computer Science 2026-05-14 Abraham Toluwase Owodunni , Orevaoghene Ahia , Sachin Kumar

Kyrgyz remains a low-resource language with limited foundational NLP tools. To address this gap, we introduce KyrgyzBERT, the first publicly available monolingual BERT-based language model for Kyrgyz. The model has 35.9M parameters and uses…

Computation and Language · Computer Science 2025-11-26 Adilet Metinov , Gulida M. Kudakeeva , Gulnara D. Kabaeva

Existing information retrieval systems are largely constrained by their reliance on vector inner products to assess query-document relevance, which naturally limits the expressiveness of the relevance score they can produce. We propose a…

Information Retrieval · Computer Science 2025-05-02 Julian Killingback , Hansi Zeng , Hamed Zamani

Transformer models have revolutionized NLP, yet many morphologically rich languages remain underrepresented in large-scale pre-training efforts. With SindBERT, we set out to chart the seas of Turkish NLP, providing the first large-scale…

Computation and Language · Computer Science 2025-10-27 Raphael Scheible-Schmitt , Stefan Schweter

We propose a practical scheme to train a single multilingual sequence labeling model that yields state of the art results and is small and fast enough to run on a single CPU. Starting from a public multilingual BERT checkpoint, our final…

Computation and Language · Computer Science 2019-09-04 Henry Tsai , Jason Riesa , Melvin Johnson , Naveen Arivazhagan , Xin Li , Amelia Archer

Text-based foundation models have become an important part of scientific discovery, with molecular foundation models accelerating advancements in material science and molecular design.However, existing models are constrained by…

Machine Learning · Computer Science 2026-01-29 Alexius Wadell , Anoushka Bhutani , Venkatasubramanian Viswanathan

We present KUTED, a speech-to-text translation (S2TT) dataset for Central Kurdish, derived from TED and TEDx talks. The corpus comprises 91,000 sentence pairs, including 170 hours of English audio, 1.65 million English tokens, and 1.40…

Computation and Language · Computer Science 2026-04-02 Mohammad Mohammadamini , Daban Q. Jaff , Josep Crego , Marie Tahon , Antoine Laurent

Modern language models mostly take sub-words as input, a design that balances the trade-off between vocabulary size, number of parameters, and performance. However, sub-word tokenization still has disadvantages like not being robust to…

Computation and Language · Computer Science 2022-11-24 Chu-Tak Lee , Qipeng Guo , Xipeng Qiu

The Byte Pair Encoding algorithm can be safely batched to merge hundreds of pairs of tokens at a time when building up a tokenizer's vocabulary. This technique combined with reducing the memory footprint of text used in vocabulary training…

Computation and Language · Computer Science 2024-08-12 Alexander P. Morgan

Somali is a Cushitic language of the Horn of Africa with ~25 million speakers, yet no documented dedicated Somali pretraining corpus with a companion tokenizer and language-identification benchmark has been publicly released. Existing…

Computation and Language · Computer Science 2026-05-19 Khalid Yusuf Dahir

Contextual spelling correction models are an alternative to shallow fusion to improve automatic speech recognition (ASR) quality given user vocabulary. To deal with large user vocabularies, most of these models include candidate retrieval…

Computation and Language · Computer Science 2023-06-06 Alexandra Antonova , Evelina Bakhturina , Boris Ginsburg

Transformer-based models have advanced NLP, yet Hebrew still lacks a large-scale RoBERTa encoder which is extensively trained. Existing models such as HeBERT, AlephBERT, and HeRo are limited by corpus size, vocabulary, or training depth. We…

Computation and Language · Computer Science 2025-10-27 Raphael Scheible-Schmitt

In this paper, we introduce a new modeling approach of texts for handwriting recognition based on syllables. We propose a supervised syllabification approach for the French and English languages for building a vocabulary of syllables.…

Computer Vision and Pattern Recognition · Computer Science 2018-08-23 Wassim Swaileh , Thierry Paquet

Spoken query retrieval is an important interaction mode in modern information retrieval. However, existing evaluation datasets are often limited to simple queries under constrained noise conditions, making them inadequate for assessing the…

Information Retrieval · Computer Science 2026-05-14 Yuejie Li , Ke Yang , Yueying Hua , Berlin Chen , Jianhao Nie , Yueping He , Caixin Kang

State-of-the-art speech recognition systems rely heavily on three basic components: an acoustic model, a pronunciation lexicon and a language model. To build these components, a researcher needs linguistic as well as technical expertise,…

Computation and Language · Computer Science 2018-03-06 Haris Bin Zia , Agha Ali Raza , Awais Athar

Spoken language models (SLMs) typically discretize speech into high-frame-rate tokens extracted from SSL speech models. As the most successful LMs are based on the Transformer architecture, processing these long token streams with…

Computation and Language · Computer Science 2026-02-05 Nicholas Lee , Cheol Jun Cho , Alan W Black , Gopala K. Anumanchipalli
‹ Prev 1 8 9 10 Next ›