Speech Recognition in the Context of Variability: Lessons from Human Listeners
Explore how human listeners adapt to speech variability, leveraging systematic variance for robust phonetic constancy. Gain insights into cognitive processes underlying speech recognition and communication.
Auditory Attention: From Saliency to Models to Applications
Explore auditory attention models and applications, from saliency to speech recognition, understanding human-machine interactions through implicit signals like eye gaze and face pose.
Speech Recognition Research: Parallels with Astronomy Development
Explore speech recognition's state-of-the-art, drawing parallels with astronomy's development. Examine cautionary tales from astronomy and biology, encouraging audience participation.
Multilingual Speech to Speech Translation for Under-Resourced Languages
Explore cutting-edge AI techniques for seamless multilingual communication, focusing on under-resourced languages through multi-modal and transfer learning approaches.
Multilingual and Code-Switching Speech Recognition
Explore multilingual and code-switching speech recognition techniques, enhancing your understanding of advanced language processing methods.
Multilingual Speech-to-Speech Translation for Under-Resourced Languages
Explore multilingual speech-to-speech translation techniques for under-resourced languages, focusing on encoding, decoding, and analysis strategies.
Diarization in the Wild: Challenges and Opportunities
Explore challenges and opportunities of diarization in daily life recordings, focusing on technical, ethical, and legal aspects for studying spontaneous language use and its applications.
Speech Recognition on Machines: The Future
Explore the future of machine-based speech recognition with expert Bishnu S Atal, delving into cutting-edge developments and potential applications.
New Directions in Robust Automatic Speech Recognition - 2005
Explore robust speech recognition techniques, from classical approaches to modern methods addressing complex acoustic environments and non-stationary noise challenges.
Making Computers Good Listeners
Explore advanced machine learning techniques for speech and language processing, focusing on novel algorithms that outperform traditional methods in phoneme recognition and voice onset time measurement.
Deterministic Annealing for Clustering, Classification and Speech Recognition
Explore deterministic annealing for improved clustering and classification, avoiding local optima and optimizing various structures in machine learning applications.
OpenAI Realtime API - The New Era of Speech to Speech? Tested
Explore OpenAI's Realtime API for speech-to-speech applications, including voice and text interactions. Learn implementation, test prompts, and discover potential use cases.
JARVIS Never Saw It Coming - Hacking Machine Learning in Speech, Text and Face Recognition
Explore vulnerabilities in machine learning systems for speech, text, and face recognition, uncovering potential security risks and attack vectors in AI technologies.
Voice Driven Development - Who Needs a Keyboard Anyway?
Explore speech recognition as a viable alternative for programmers facing physical limitations, offering insights on tools, techniques, and workplace adaptations for voice-driven development.
JARVIS Never Saw It Coming - Hacking Machine Learning in Speech, Text and Face Recognition
Explore hacking techniques for machine learning systems in speech, text, and facial recognition, including exploits, backdoors, and adversarial attacks. Live demo included.
Machine Duping - Pwning Deep Learning Systems
Explore vulnerabilities in deep learning systems and learn techniques to manipulate image recognition, speech recognition, and phishing detection through practical demonstrations and attack methodologies.
Exploring Innovations in AI
Experts discuss AI's current applications, future potential, and impact on industries like biology and medicine. Explore unexpected uses, technological breakthroughs, and societal implications of artificial intelligence.
Emotion and Touch in Virtual Reality
Explore emotion and touch in VR for enhanced social interaction. Learn about haptic devices, tactile sensations, and emotion recognition to improve long-distance communication and create more immersive experiences.
Revisiting "Hole in the Wall" Computing - Private Smart Speakers and Public Slum Settings
Exploring smart speaker technology in Indian slum communities, addressing challenges and opportunities for public deployment, and discussing design considerations for resource-constrained environments.
Assistive Augmentation - Lip Reading with AI
Explore AI-powered lip reading technology as an assistive solution for the deaf and hard of hearing, addressing challenges and showcasing implementation for improved accessibility in various settings.
Speech and Emotion Recognition
Explore cutting-edge research in speech and emotion recognition technologies, examining innovative approaches and their potential applications in human-computer interaction.