Výsledky vyhledávání - "Keith Francis"

Report

Cross-Lingual Conversational Speech Summarization with Large Language Models

Autor: Nelson, Max, Wotherspoon, Shannon, Keith, Francis, Hartmann, William, Snover, Matthew

Cross-lingual conversational speech summarization is an important problem, but suffers from a dearth of resources. While transcriptions exist for a number of languages, translated conversational speech is rare and datasets containing summaries are no

Externí odkaz: http://arxiv.org/abs/2408.06484

Zobrazit plný text záznamu

Report

Training Autoregressive Speech Recognition Models with Limited in-domain Supervision

Autor: Li, Chak-Fai, Keith, Francis, Hartmann, William, Snover, Matthew

Advances in self-supervised learning have significantly reduced the amount of transcribed audio required for training. However, the majority of work in this area is focused on read speech. We explore limited supervision in the domain of conversationa

Externí odkaz: http://arxiv.org/abs/2210.15135

Zobrazit plný text záznamu

Report

Combining Unsupervised and Text Augmented Semi-Supervised Learning for Low Resourced Autoregressive Speech Recognition

Autor: Li, Chak-Fai, Keith, Francis, Hartmann, William, Snover, Matthew

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute -- conversationa

Externí odkaz: http://arxiv.org/abs/2110.15836

Zobrazit plný text záznamu

Review

The Story of Physics T. Padmanabhan Keith Francis Avinash Deshpande

Autor: Keshavamurthy, Srihari

Publikováno v: Current Science, 2008 Aug . 95(4), 532-532.

Externí odkaz: https://www.jstor.org/stable/24102619

Zobrazit plný text záznamu

Report

Overcoming Domain Mismatch in Low Resource Sequence-to-Sequence ASR Models using Hybrid Generated Pseudotranscripts

Autor: Li, Chak-Fai, Keith, Francis, Hartmann, William, Snover, Matthew, Kimball, Owen

Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for seq2seq mod

Externí odkaz: http://arxiv.org/abs/2106.07716

Zobrazit plný text záznamu

Akademický článek

The Influence of Teacher Readiness and Learning Facilities on Student Learning Motivation: Blended Learning as a Mediating Variable

Autor: Mario Parinsi, Yosua Fitsgerald Ratumbuisang, Keith Francis Ratumbuisang

Publikováno v: Didaktika: Jurnal Kependidikan, Vol 13, Iss 1 (2024)

Student learning motivation after the Covid-19 pandemic has become an interesting topic, student learning motivation plays an important role in the learning process. Problems with student learning motivation can arise due to a lack of teacher readine

Externí odkaz: https://doaj.org/article/93559aad611046c0a1e8e04ca7a6ee0e

Zobrazit plný text záznamu