scholar.google.com › citations
Sep 18, 2023 · In this paper, we propose a new strategy for adapting ASR models to new target domains without any text or speech from those domains.
In this paper, we propose a new strategy for adapting ASR models to new target domains without any text or speech from those domains.
Apr 18, 2024 · Towards high-performance and low-latency feature-based speaker adaptation of conformer speech recognition systems.
This paper proposes a novel data synthesis pipeline that uses a Large Language Model (LLM) to generate a target domain text corpus.
Corpus Synthesis for Zero-Shot ASR Domain Adaptation Using Large ...
www.researchgate.net › ... › ASR
Apr 16, 2024 · Recent advances in Large Language Models (LLM) have shown impressive improvements in language understanding tasks [5] through their emergent ...
Sep 18, 2023 · To accomplish this, we propose a novel data synthesis pipeline that uses a Large Language Model (LLM) to generate a target domain text corpus, ...
Sep 18, 2023 · Major contributions: (1) We demonstrate that text cor- pus synthesis using LLMs enables zero-shot ASR domain adaptation. (2) Our proposed in- ...
Mar 27, 2024 · Sep 24, 2023 • 1 · Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models. Paper • 2309.10707 • Published Sep 18 ...
Corpus Synthesis for Zero-shot ASR Domain Adaptation using Large Language Models. While Automatic Speech Recognition (ASR) systems are widely used in many ...
In this paper, we propose a new strategy for adapting ASR models to new target domains without any text or speech from those domains. Automatic Speech ...