Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions
The deep learning based time-domain models, e.g. Conv-TasNet, have shown great potential in both single-channel and multi-channel speech enhancement. However, many experiments on the time-domain speech enhancement model are done in simulated conditions, and it is not well studied whether the good performance can generalize to real-world scenarios. In this paper, we aim to provide an insightful investigation of applying multi-channel Conv-TasNet based speech enhancement to both simulation and real data. Our preliminary experiments show a large performance gap between the two conditions in terms of the ASR performance. Several approaches are applied to close this gap, including the integration of multi-channel Conv-TasNet into the beamforming model with various strategies, and the joint training of speech enhancement and speech recognition models. Our experiments on the CHiME-4 corpus show that our proposed approaches can greatly reduce the speech recognition performance discrepancy between simulation and real data, while preserving the strong speech enhancement capability in the frontend.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech Enhancementspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition
We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionVoltage mapping in subcellular nanodomains using electro-diffusion modeling
Voltage distribution in sub-cellular micro-domains such as neuronal synapses, small protrusions or dendritic spines regulates the opening and closing of ionic channels, energy production and thus cellular homeostasis and…
Modelling modal gating of ion channels with hierarchical Markov models
Many ion channels spontaneously switch between different levels of activity. Although this behaviour known as modal gating has been observed for a long time it is currently not well understood. Despite the fact that appr…
Where Detectors Fail: Closing the Tail-Domain Gap with Expert-Guided Mutual Distillation
Multimodal fake news detectors often generalize poorly across domains because they learn to trust unreliable evidence: domain-specific shortcuts amplified by imbalanced data and semantically inconsistent text-image pairs…
Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM
Loop closing and relocalization are crucial techniques to establish reliable and robust long-term SLAM by addressing pose estimation drift and degeneration. This article begins by formulating loop closing and relocalizat…
Point Cloud RegistrationPose EstimationRetrieval