Importance of Different Temporal Modulations of Speech: A Tale of Two Perspectives

31 Mar 2022  ·  Samik Sadhu, Hynek Hermansky ·

How important are different temporal speech modulations for speech recognition? We answer this question from two complementary perspectives. Firstly, we quantify the amount of phonetic \textit{information} in the modulation spectrum of speech by computing the mutual information between temporal modulations with frame-wise phoneme labels. Looking from another perspective, we ask - which speech modulations an Automatic Speech Recognition (ASR) system prefers for its operation. Data-driven weights are learned over the modulation spectrum and optimized for an end-to-end ASR task. Both methods unanimously agree that speech information is mostly contained in slow modulation. Maximum mutual information occurs around 3-6 Hz which also happens to be the range of modulations most preferred by the ASR. In addition, we show that the incorporation of this knowledge into ASRs significantly reduces their dependency on the amount of training data.

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here