Code-switching (CS), the alternating use of two or more languages, challenges automatic speech recognition (ASR) due to scarce training data and linguistic similarities. The lack of dedicated CS datasets limits ASR performance, as most models rely on monolingual or mixed-language corpora that fail to reflect real-world CS patterns. This issue is critical in multilingual societies where CS occurs in informal and formal settings. A key example is Catalan-Spanish CS, widely used in media and parliamentary speeches. In this work, we improve ASR for Catalan-Spanish CS by exploring three strategies: (1) generating synthetic CS data, (2) concatenating monolingual audio, and (3) leveraging real CS data with language tokens. We extract CS data from Catalan speech corpora and fine-tune OpenAI’s Whisper models, making them available on Hugging Face. Results show that combining a modest amount of synthetic CS data with the dominant language token yields the best transcription performance.

Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, Vishrav Chaudhary, Luis Chiruzzo, Angela Fan, John Ortega, Ricardo Ramos, Annette Rios, Ivan Vladimir Meza Ruiz, Gustavo Giménez-Lugo, Elisabeth Mager, Graham Neubig, Alexis Palmer, Rolando Coto-Solano, Thang Vu, Katharina Kann. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Indigenous languages of the American continent are highly diverse. However, they have received little attention from the technological perspective. In this paper, we review the research, the digital resources and the available NLP systems that focus on these languages. We present the main challenges and research questions that arise when distant languages and low-resource scenarios are faced. We would like to encourage NLP research in linguistically rich and diverse areas like the Americas.

Katharina Kann, Jesus Manuel Mager Hois, Ivan Vladimir Meza-Ruiz, Hinrich Schütze. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

July 01 2010 Mechanical Love. Phie Ambo. (2009, Icarus Films.) $390, 52 min. Carlos Gershenson, Carlos Gershenson Search for other works by this author on: This Site Google Scholar Iván V. Meza, Iván V. Meza Search for other works by this author on: This Site Google Scholar Héctor Avilés, Héctor Avilés Search for other works by this author on: This Site Google Scholar Luis A. Pineda Luis A. Pineda Search for other works by this author on: This Site Google Scholar Author and Article Information Carlos Gershenson Iván V. Meza Héctor Avilés Luis A. Pineda *Contact author. **Instituto de Investigaciones en Matematicas Aplicadas y en Sistemas Universidad Nacional Autonoma de Mexico Ciudad Universitaria, Apdo. Postal 20-726/Admon No. 20 01000, Mexico, D.F. Mexico. E-mail: [email protected] Online Issn: 1530-9185 Print Issn: 1064-5462 © 2010 Massachusetts Institute of Technology2010MIT Press Artificial Life (2010) 16 (3): 269–270. https://doi.org/10.1162/artl_r_00004 Cite Icon Cite Permissions Share Icon Share Twitter LinkedIn Views Icon Views Article contents Figures & tables Video Audio Supplementary Data Peer Review Search Site Citation Carlos Gershenson, Iván V. Meza, Héctor Avilés, Luis A. Pineda; Mechanical Love. Phie Ambo. (2009, Icarus Films.) $390, 52 min.. Artif Life 2010; 16 (3): 269–270. doi: https://doi.org/10.1162/artl_r_00004 Download citation file: Ris (Zotero) Reference Manager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu nav search search input Search input auto suggest search filter All ContentAll JournalsArtificial Life Search Advanced Search This content is only available as a PDF. © 2010 Massachusetts Institute of Technology2010MIT Press Article PDF first page preview Close Modal You do not currently have access to this content.

Robust spoken language understanding (SLU) is a key component of spoken dialogue systems. Recent statistical approaches to this problem require additional resources (e.g. gazetteers, grammars, syntactic treebanks) which are expensive and time-consuming to produce and maintain. However, simple datasets annotated only with slot-values are commonly used in dialogue systems development, and are easy to collect, automatically annotate, and update. We show that it is possible to reach state-of-the-art performance using minimal additional resources, by using Markov logic networks (MLNs). We also show that performance can be further improved by exploiting long distance dependencies between slot-values. For example, by representing such features in MLNs, but without using a gazetteer, we outperform the hidden vector state (HVS) model of He and Young 2006 (1.26% improvement, a 13% error reduction).