Mask scalar prediction for improving robust automatic speech recognition
Using neural network based acoustic frontends for improving robustness of streaming automatic speech recognition (ASR) systems is challenging because of the causality constraints and the resulting distortion that the frontend processing introduces in speech. Time-frequency masking based approaches have been shown to work well, but they need additional hyper-parameters to scale the mask to limit speech distortion. Such mask scalars are typically hand-tuned and chosen conservatively. In this work, we present a technique to predict mask scalars using an ASR-based loss in an end-to-end fashion, with minimal increase in the overall model size and complexity. We evaluate the approach on two robust ASR tasks: multichannel enhancement in the presence of speech and non-speech noise, and acoustic echo cancellation (AEC). Results show that the presented algorithm consistently improves word error rate (WER) without the need for any additional tuning over strong baselines that use hand-tuned hyper-parameters: up to 16% for multichannel enhancement in noisy conditions, and up to 7% for AEC.
Code (0)
등록된 구현이 없습니다.
Tasks
Acoustic echo cancellationAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Predictionspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization
Low latency speech human-machine communication is becoming increasingly necessary as speech technology advances quickly in the last decade. One of the primary factors behind the advancement of speech technology is self-s…
Self-Supervised LearningSpeech RecognitionData AugmentationSupervision-Guided Codebooks for Masked Prediction in Speech Pre-training
Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)ClusteringSelf-Supervised Learning+2Accent-Invariant Automatic Speech Recognition via Saliency-Driven Spectrogram Masking
Pre-trained transformer-based models have significantly advanced automatic speech recognition (ASR), yet they remain sensitive to accent and dialectal variations, resulting in elevated word error rates (WER) in linguisti…
Speech RecognitionData AugmentationLearning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction
Video recordings of speech contain correlated audio and visual information, providing a strong signal for speech representation learning from the speaker's lip movements and the produced sound. We introduce Audio-Visual …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)LipreadingLip Reading+4CR-CTC: Consistency regularization on CTC for improved speech recognition
Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performan…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Computational EfficiencyDecoder+2