Efficient Trainable Front-Ends for Neural Speech Enhancement
Many neural speech enhancement and source separation systems operate in the time-frequency domain. Such models often benefit from making their Short-Time Fourier Transform (STFT) front-ends trainable. In current literature, these are implemented as large Discrete Fourier Transform matrices; which are prohibitively inefficient for low-compute systems. We present an efficient, trainable front-end based on the butterfly mechanism to compute the Fast Fourier Transform, and show its accuracy and efficiency benefits for low-compute neural speech enhancement models. We also explore the effects of making the STFT window trainable.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech EnhancementSimilar Papers 제목 키워드 기반
Frontend Token Enhancement for Token-Based Speech Recognition
Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these rep…
Self-Supervised LearningSpeech RecognitionESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
This paper presents recent progress on integrating speech separation and enhancement (SSE) into the ESPnet toolkit. Compared with the previous ESPnet-SE work, numerous features have been added, including recent state-of-…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Robust Speech RecognitionSpeech Enhancement+4Deep Xi as a Front-End for Robust Automatic Speech Recognition
Current front-ends for robust automatic speech recognition(ASR) include masking- and mapping-based deep learning approaches to speech enhancement. A recently proposed deep learning approach toa prioriSNR estimation, call…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Deep LearningSpeech Enhancement+2ROBUST SPEECH COMMAND RECOGNITION USING LABEL-DRIVEN TIME-FREQUENCY MASKING
Speech enhancement driven robust Automatic Speech Recognition (ASR) systems typically require parallel corpus with noisy and clean speech utterances for training. Moreover, many studies have reported that such front-ends…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)ClassificationSpeech Enhancement+2Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends
Speech enhancement is often used as a front-end for robust ASR, yet recurrent temporal and cross-band modules introduce sequential dependencies that reduce parallel efficiency. In this paper, we present a sequence-parall…
Speech Enhancement