Mark Gales

Deep Activation Mixture Model for Speech Recognition

2017

Deep learning approaches achieve state-of-the-art performance in a range of applications, including speech recognition. However, the parameters of the deep neural network (DNN) are hard to interpret, which makes regularisation and adaptation to speaker or …

Surprise Languages: Rapid-Response Cross-Language IR

2019 · Edinburgh Research Explorer (University of Edinburgh)

Sixteen years ago, the first "surprise language exercise" was conducted, in Cebuano. The evaluation goal of a surprise language exercise is to learn how well systems for a new language can be quickly built. This …

Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems

2021 · arXiv (Cornell University)

Transformer models have achieved state-of-the-art results in a wide range of NLP tasks including summarization. Training and inference using large transformer models can be computationally expensive. Previous work has focused on one important bottleneck, the …

Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment

2024 · arXiv (Cornell University)

Large Language Models (LLMs) are powerful zero-shot assessors used in real-world situations such as assessing written exams and benchmarking systems. Despite these critical applications, no existing work has analyzed the vulnerability of judge-LLMs to adversarial …

Cross-Lingual Transfer Learning for Speech Translation

2024 · arXiv (Cornell University)

There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech foundation …