Machine learning methods for language

SUFFIX RETRIEVAL-AUGMENTED LANGUAGE MODELING

Knowledge Transfer For On-Device Speech Emotion Recognition with Neural Structured Learning

Improving Disfluency Detection with Multi-scale Self Attention and Contrastive Learning

Targeted Adversarial Attacks against Neural Machine Translation

RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness

Dynamic Fair Node Representation Learning

Less is more: A unified architecture for device-directed speech detection with multiple invocation types

Pyramid Dynamic Inference: Encouraging Faster Inference via Early Exit Boosting

Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead

Interpolation of spatial room impulse responses using partial optimal transport

Performance comparison of TTS models for Brazilian Portuguese to establish a baseline

LAST: Scalable Lattice-Based Speech Modelling in JAX