SLT 2026 (IEEE Spoken Language Technology) is a CCF C conference held in Palermo, Sicily, Italy on 2026-12-13. The paper submission deadline is 2026-06-24 (extended). Acceptance notifications are sent on 2026-09-08.
The IEEE Spoken Language Technology (SLT) Workshop, held biennially, brings together leading researchers from academia and industry in a focused and collaborative environment. As a pivotal forum for discussing emerging developments and shared challenges in spoken language technology, SLT fosters meaningful dialogue, the exchange of cutting-edge research, and the advancement of the field.
Transforming how we connect and innovate, spoken language technology profoundly impacts human progress by driving the future of interaction, accelerating innovation, ensuring greater accessibility, and enabling seamless human-machine interaction. Its impact extends across numerous domains, including education and healthcare, where it is transforming how technology is developed and deployed. We look forward to welcoming you to SLT 2026 for an enriching experience as we explore the latest innovations and continue pushing the frontiers of this dynamic field.
Topics
We are calling for submissions in all areas of spoken language processing, particularly focusing on the following topics:
Automatic speech recognition
Conversational/multi-speaker ASR
Far-field speech processing
Speech separation and enhancement
Speaker and language recognition
Speaker diarization
Spoken language understanding
Spoken dialog systems
Low resource/multilingual speech processing
Spoken language processing
Spoken document retrieval
Speech-to-speech translation
Text-to-speech systems
Speech summarization
New applications of automatic speech recognition
Audio-visual/multimodal speech processing
Emotion recognition from speech
Large language models for spoken language processing
Speech foundation models
Self-supervised and representation learning for speech
Child speech/language processing
Special Theme: Spoken Language Technology for Social Wellbeing in the Digital Privacy Era
Since the theme of this year is Spoken Language Technology for Social Wellbeing in the Digital Privacy Era, the following key topics are also proposed:
Voice Technology in Healthcare
Speech Processing for Assistive Healthcare Technologies
Assistive Hearing and Speaking Technologies
Voice-Activated Virtual Healthcare Assistants
Speech Technologies for Telehealth and Remote Care
Privacy-preserving speech recognition
Privacy in Voice Biometrics and Speaker Identification
Robustness of speech technologies against malicious activities, adversarial attacks, and threat models
Fairness, bias, and accountability in speech systems
Spoofing and deepfake detection, attribution, and characterization
Forensic and investigative applications
Voice Anonymization Techniques
Integrity verification, watermarking, and traceability for voice technologies
暂无评论。