Multiple Confidence Gates For Joint Training Of SE And ASR
Joint training of speech enhancement model (SE) and speech recognition model (ASR) is a common solution for robust ASR in noisy environments. SE focuses on improving the auditory quality of speech, but the enhanced feature distribution is changed, which is uncertain and detrimental to the ASR. To tackle this challenge, an approach with multiple confidence gates for jointly training of SE and ASR is proposed. A speech confidence gates prediction module is designed to replace the former SE module in joint training. The noisy speech is filtered by gates to obtain features that are easier to be fitting by the ASR network. The experimental results show that the proposed method has better performance than the traditional robust speech recognition system on test sets of clean speech, synthesized noisy speech, and real noisy speech.
Code (0)
등록된 구현이 없습니다.
Tasks
Robust Speech RecognitionSpeech Enhancementspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Confidence-gated training for efficient early-exit neural networks
Early-exit neural networks reduce inference cost by enabling confident predictions at intermediate layers. However, joint training often leads to gradient interference, with deeper classifiers dominating optimization. We…
Shape-aware Multi-Person Pose Estimation from Multi-View Images
In this paper we contribute a simple yet effective approach for estimating 3D poses of multiple people from multi-view images. Our proposed coarse-to-fine pipeline first aggregates noisy 2D observations from multiple cam…
3D Multi-Person Pose EstimationMulti-Person Pose EstimationPose EstimationEvaluating and Calibrating LLM Confidence on Questions with Multiple Correct Answers
Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied under single-answer question answering. In this paper, we show that the…
Question AnsweringPiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains
Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting the one with the highest reward. The key challenge for r…
Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMs
Large vision-language models (LVLMs) demonstrate strong visual question answering (VQA) capabilities but are shown to hallucinate. A reliable model should perceive its knowledge boundaries-knowing what it knows and what …
Visual Question Answering