A review of deep learning techniques for speech processing
The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …
learning. The use of multiple processing layers has enabled the creation of models capable …
A Framework for Enhancing Behavioral Science Research with Human-Guided Language Models
J Scheuerman, D Acklin - Proceedings of the AAAI Symposium Series, 2024 - ojs.aaai.org
Many behavioral science studies result in large amounts of unstructured data sets that are
costly to code and analyze, requiring multiple reviewers to agree on systematically chosen …
costly to code and analyze, requiring multiple reviewers to agree on systematically chosen …
AdaBERT-CTC: Leveraging BERT-CTC for text-only domain adaptation in ASR
Abstract End-to-end (E2E) automatic speech recognition (ASR) models are becoming
increasingly popular in commercial applications, such as virtual assistants, closed …
increasingly popular in commercial applications, such as virtual assistants, closed …
[PDF][PDF] Improving Speech Recognition with Prompt-based Contextualized ASR and LLM-based Re-predictor
NMT Anh, TH Sy - isca-archive.org
In recent years, advancements in automatic speech recognition (ASR) systems have led to
their widespread use in applications such as call center bots and virtual assistants …
their widespread use in applications such as call center bots and virtual assistants …
Domain-specific parameter pre-fixes for tuning automatic speech recognition
Abstract Domain-specific parameters may be used for tuning speech processing. A pre-
trained transformer-based language model may train domain-specific parameters using …
trained transformer-based language model may train domain-specific parameters using …