In this work, we first propose a general evaluation criterion that requires an ASR error robust model to perform well on both transcription and ASR hypothesis.
Aug 7, 2020 · Abstract. A modern Spoken Language Understanding (SLU) system usually contains two sub-systems, Automatic Speech Recogni- tion (ASR) and ...
Jan 5, 2024 · Here we introduce a method that utilizes the ASR system's lattice output instead of relying solely on the top hypothesis, aiming to encapsulate speech ...
Oct 26, 2020 · In this work, we first propose a general evaluation criterion that requires an ASR error robust model to perform well on both transcription and ...
A general evaluation criterion is proposed that requires an ASR error robust model to perform well on both transcription and ASR hypothesis and robustness ...
To build ASR an error robust SLU system, Ruan et al. [4] have proposed a loss function that uses both the ASR hypothesis and the gold text, but this technique ...
Jan 5, 2024 · Here we introduce a method that utilizes the ASR system's lattice output instead of relying solely on the top hypothesis, aiming to encapsulate speech ...
People also ask
What is ASR in speech recognition?
How is language model used in ASR?
Aug 16, 2024 · In this paper, we propose Prototype Calibration and Asymmetric Decoupling (PCAD) to tackle the above issues. For sample bias, we adopt a proto-.
Aug 11, 2024 · An effective approach to mitigate the detrimen- tal impact of errors arising from ASR is to learn error-robust representations for SLU. D'Haro ...
We propose MoE-SLU, an ASR-Robust SLU framework based on the mixture-of-experts technique. Specifically, we first introduce three strategies to generate ...