← Search

Andrei Andrusenko

2 accepted papers

2024

SALM: Speech-Augmented Language Model with in-Context Learning for Speech Recognition and Translation

ICASSP 2024accepted

We present a novel Speech Augmented Language Model (SALM) with multitask and in-context learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech input and associated task instructions. The unified SALM not only achieve…

Cited by 0SourceScholar
2023

UCONV-Conformer: High Reduction of Input Sequence Length for End-to-End Speech Recognition

ICASSP 2023accepted

Optimization of modern ASR architectures is among the highest priority tasks since it saves many computational resources for model training and inference. The work proposes a new Uconv-Conformer architecture <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlin…

Cited by 0SourceScholar