Información de la Revista

Computer Speech & Language

Por favor Iniciar sesión para ver el sitio web de la revista
Cuenta gratuita: consulta los sitios oficiales, sigue las fechas límite y recibe recordatorios por correo.
Iniciar sesión Registrarse

Factor de Impacto:
3.0
Editor:
Elsevier
ISSN:
0885-2308
Vistas:
30766
Seguidores:
30

Solicitud de Artículos

Computer Speech & Language is an academic journal published by Elsevier. (ISSN 0885-2308, impact factor 3.0, CCF C).

An official publication of the International Speech Communication Association (ISCA) Computer Speech & Language publishes reports of original research related to the analysis, recognition, understanding, production, synthesis, coding and mining of speech and spoken language, including spoken language dialogue systems and speech-based interaction with ‘intelligent’ artefacts, and their wide-ranging applications. The journal provides a focus for this work, and encourages an interdisciplinary approach to speech and spoken language research and technology. Thus contributions from all of the related fields are welcomed in the form of reports of theoretical or experimental studies, reviews, and pertaining to models and their implementation, or reports of fundamental research leading to the improvement of such models. Research Areas Include Algorithms and models for speech recognition and synthesis Natural language processing for speech understanding and generation Computational models of spoken language discourse and dialogue Speech and spoken-language inclusive multimodal approaches and systems Information retrieval, extraction and summarization of spoken language media Speaker and spoken language recognition Computational models of speech production and perception Signal processing for speech analysis, enhancement and transformation Evaluation of speech-based interactive systems Applications of speech and spoken language technologies Note that we are no longer accepting submissions devoted to pure Natural Language Processing NLP (i.e. all new manuscripts must address some aspect of spoken language processing).
Última actualización por Dou Sun el

Special Issues

Special Issue on Evaluation of speech and speech synthesis Día de Entrega: 2026-07-31 Synthetic speech has advanced to a point where its quality and diversity challenge the boundaries of existing evaluation methods. Frameworks such as MOS and MUSHRA were designed to measure transmission quality rather than to assess speech as such; they were never intended to capture the communicative or functional properties of speech when transmission is no longer the limiting factor. In contemporary systems, performance ought instead to be defined by how well the speech fulfils its intended task, role, or utility. The Special Issue therefore asks how evaluation can be made more responsive to this new landscape: one in which human and synthetic speech can, and should, be assessed by comparable principles tied to task and situation. Much of today’s evaluation practice still relies on comparing synthetic speech to static recordings of human voices. Such tests can be useful for measuring surface similarity, but they ignore the dynamic and situational aspects that determine whether speech actually fulfils its purpose. Human speakers continuously adapt timing, prosody, and style to the communicative setting and to the role or persona they embody. A synthetic voice should be expected to perform similarly: it should use a speaking style suited to the situation or task, be it audiobook narration, dialogue interaction, public announcement, or personalised replacement voice, and align it with the intended persona, be that a robot, a disembodied assistant, a child, or an adult. This Special Issue particularly seeks evaluations that capture such situational and functional adequacy, rather than limiting comparison to perceived “human-likeness.” Guest editors: Dr. Sébastien Le Maguer (Executive Guest Editor), University of Helsinki, Helsinki, Finland; Email: [email protected] Prof. Jens Edlund, KTH Royal Institute of Technology, Stockholm, Sweden; Email: [email protected] Dr. Christina Tånnander, MTM, Swedish Agency for Accessible Media and KTH Royal Institute of Technology, Stockholm, Sweden; Email: [email protected] Prof. Petra Wagner, Bielefeld University, Bielefeld, Germany; Email: [email protected] Special issue information: We invite contributions that reinvent, extend or refine evaluation practice in these directions, including but not limited to studies that: propose concrete alternatives to established evaluation paradigms, demonstrating that more informative and diagnostically useful practices are both possible and practicable; investigate the generalisability of established evaluation schemes across different applications or tasks, or compare various evaluation schemes within a single application domain; align measurement with real-world use, broadening evaluation perspectives through situated examples from accessibility, education, healthcare, entertainment, and other fields; provide guidance for future research, consolidating lessons into good practices and identifying the conceptual and methodological challenges that remain; or transfer or adapt evaluation practices from neighbouring fields such as speech therapy, HCI, or psychology. Manuscript submission information: Important Dates: Submission Open Date: December 1, 2025 Submission Deadline: July 31, 2026 Editorial Acceptance Deadline: March 31, 2027 Submission Guidelines: All manuscripts should be submitted electronically through Editorial Manager® at https://www.editorialmanager.com/ycsla/default.aspx. When submitting papers, please select the Article Type as "VSI: Speech Eval & Synthesis". Authors should prepare their manuscripts according to the "Guide for Authors" of the Computer Speech & Language outlined at the journal website. All papers will be peer-reviewed following a regular reviewing procedure. For any further information, the authors may contact the Guest Editors. Keywords: speech synthesis; evaluation https://www.sciencedirect.com/special-issue/328510/evaluation-of-speech-and-speech-synthesis
Última actualización por Admin Agent el
Special Issue on Speaker Characterization Beyond Words: Identity, Health and Emotion from Speech Día de Entrega: 2026-10-31 Speech technologies are undergoing a profound transformation. Recent advances in self-supervised learning, large-scale pretraining, and foundation models have reshaped the way speech representations are learned, evaluated, and deployed. In parallel, speaker and language technologies, traditionally centered on identification and verification, are expanding toward broader forms of speaker characterization, including the modeling of paralinguistic traits, emotional states, speech-affecting conditions, and other speaker attributes. These technological advances open new opportunities for multilingual access, personalization, health-related applications, and large-scale real-world deployment. At the same time, they raise critical questions regarding robustness, fairness, bias, privacy, and security. As speech systems become increasingly capable of inferring sensitive information about individuals, careful scientific and ethical examination is required. Odyssey 2026 – The Speaker and Language Recognition Workshop, reflects this evolution of the field. While the Odyssey series has historically focused on speaker and language recognition systems, the 2026 edition explicitly broadens its scope toward comprehensive speaker characterization and its societal implications. The workshop brings together researchers, industry practitioners, and policymakers to discuss both methodological advances and emerging challenges, including health-related applications and privacy-aware modeling. Guest editors: Alberto Abad (Executive Guest Editor), INESC-ID & Instituto Superior Técnico, Lisbon, Portugal​ Jose A. Gonzalez-Lopez, University of Granada, Granada, Spain Alfonso Ortega, University of Zaragoza, Zaragoza, Spain Alicia Lozano-Diez, Universidad Autónoma de Madrid, Madrid, Spain Javier Hernando, Universitat Politècnica de Catalunya, Barcelona, Spain Special issue information: This Special Issue of Computer Speech & Language aims to capture the state of the art at this pivotal moment. It seeks to consolidate recent advances, critically assess emerging methodologies, and provide a forward-looking perspective on the next generation of speaker and language technologies. The broader objectives of this Special Issue are: To document recent advances in speaker and language recognition in the era of self-supervised and foundation models. To explore emerging paradigms in speaker characterization beyond traditional recognition tasks. To examine robustness, multilinguality, and real-world deployment challenges. To foster research on fairness, bias mitigation, privacy, and security in speech-based modeling. To highlight interdisciplinary connections, including applications in health and speech-relatedconditions. We welcome original and substantially extended contributions addressing theoretical, methodological, and applied aspects of speaker and language technologies. Topics of interest include, but are not limited to: Speaker verification, identification, and diarization Language recognition and multilingual modeling Self-supervised learning and foundation models for speech Representation learning for speaker and language characterization Domain adaptation and robustness to noise and mismatch Paralinguistics, speaker traits, and affective speech analysis Speaker characterization in health-related applications Fairness, bias mitigation, and responsible AI in speech technologies Privacy, security, and adversarial aspects of speaker modeling Evaluation methodologies, benchmarking, and reproducibility Multimodal approaches integrating speech with other modalities Large-scale deployment and real-world system evaluation Submissions must present significant extensions beyond any prior conference publication and will undergo the journal’s standard peer-review process. Manuscript submission information: Important Dates: Submission Open Date: July 1, 2026 Submission Deadline: October 31, 2026 Editorial Acceptance Deadline: February 28, 2027 Submission Guidelines: All manuscripts should be submitted electronically through Editorial Manager® at https://www.editorialmanager.com/ycsla/default.aspx. When submitting papers, please select the Article Type as "VSI: Speaker Characterization". Authors should prepare their manuscripts according to the "Guide for Authors" of the Computer Speech & Language outlined at the journal website. All papers will be peer-reviewed following a regular reviewing procedure. For any further information, the authors may contact the Executive Guest Editor, Assoc. Prof. Alberto Abad ([email protected]). Keywords: speaker and language characterization; emotion recognition; speech affecting conditions and health applications; trustworthy and privacy in speaker characterization https://www.sciencedirect.com/special-issue/333819/speaker-characterization-beyond-words-identity-health-and-emotion-from-speech
Última actualización por Admin Agent el
Special Issue on Acoustical Intelligence in the Wild: Advancing Acoustic Signal Understanding in Open Environments Día de Entrega: 2027-05-31 The last decade has witnessed remarkable progress in speech and audio signal understanding. However, most state-of-the-art models are trained on static datasets under a "closed-set" assumption. In contrast, the real-world acoustic environment is inherently dynamic and continuously evolving. A truly intelligent system must not only recognize known sounds but also adapt to new speech patterns, novel acoustic events, and changing background conditions over time without catastrophic forgetting. This Special Issue focuses on the frontier of Continual and Life-long Learning for Speech and Audio. When deployed "in the wild," systems encounter a stream of out-of-distribution (OOD) data. The challenge lies in transitioning from static inference to dynamic adaptation: enabling models to incrementally learn from new acoustic environments while maintaining robustness on previously mastered tasks. This is particularly critical for personalized voice assistants, longterm environmental monitoring, and adaptive hearing aids where the acoustic distribution shifts daily. We invite original research that addresses the lifecycle of acoustic models in the wild. Key topics include, but are not limited to: Class-Incremental Learning for New Sound Events and Spoken Languages. Online Domain Adaptation for Speech Enhancement in Non-stationary Noise. Mitigating Catastrophic Forgetting in Large-scale Audio Pre-trained Models. Open-set Detection and Active Learning for Unlabeled Acoustic Streams. Memory-efficient Continual Learning for Edge Audio Devices. Privacy-preserving Life-long Learning for Personalized Speech Interfaces. By bridging the gap between continual machine learning and audio signal processing, this issue seeks to establish a new paradigm for "Living" acoustic systems—models that grow and refine their understanding alongside the ever-changing soundscapes they inhabit. Guest editors: Prof. Kele Xu (Executive Guest Editor) National University of Defense Technology, Changsha, China Email:[email protected] Research Interests: Computer audition, Multimodal machine learning Dr. Boqing Zhu National University of Defense Technology, Changsha, China Email: [email protected] Research Interests: Continual Leaning, acoustic Signal Processing, and Underwater Acoustic Prof. Qian Kun Beijing Institute of Technology, Beijing, China Email: [email protected] Research Interests: Computer Audition, Signal Processing, Healthcare Prof. Zixing Zhang Hunan University, Changsha, China Email: [email protected] Manuscript submission information: Important Dates: Submission Open Date: April 15, 2026 Submission Deadline: May 31, 2027 Editorial Acceptance Deadline: June 30, 2027 Submission Guidelines: All manuscripts should be submitted electronically through Editorial Manager® at https://www.editorialmanager.com/ycsla/default.aspx. When submitting papers, please select the Article Type as "VSI: Acoustical Intelligence in the Wild". Authors should prepare their manuscripts according to the "Guide for Authors" of the Computer Speech & Language outlined at the journal website. All papers will be peer-reviewed following a regular reviewing procedure. For any further information, the authors may contact the Guest Editors. Keywords: Continual Learning; Robust Speech Processing; Open-World Acoustic Intelligence; Life-long Machine Audition; Non-stationary Signal Understanding https://www.sciencedirect.com/special-issue/332571/acoustical-intelligence-in-the-wild-advancing-acoustic-signal-understanding-in-open-environments
Última actualización por Admin Agent el

Las personas que vieron esto también vieron

Revistas Relacionadas

Conferencias Relacionadas

Comentarios 0

Aún no hay comentarios.

Por favor Iniciar sesión para publicar un comentario