End-to-End Speech Recognition with High-Frame-Rate Features Extraction
share
State-of-the-art end-to-end automatic speech recognition (ASR) extracts acoustic features from input speech signal every 10 ms which corresponds to a frame rate of 100 frames/second. In this paper, we investigate the use of high-frame-rate features extraction in end-to-end ASR. High frame rates of 200 and 400 frames/second are used in the features extraction and provide additional information for end-to-end ASR. The effectiveness of high-frame-rate features extraction is evaluated independently and in combination with speed perturbation based data augmentation. Experiments performed on two speech corpora, Wall Street Journal (WSJ) and CHiME-5, show that using high-frame-rate features extraction yields improved performance for end-to-end ASR, both independently and in combination with speed perturbation. On WSJ corpus, the relative reduction of word error rate (WER) yielded by high-frame-rate features extraction independently and in combination with speed perturbation are up to 21.3 WER reductions are up to 2.8 by microphone arrays and up to 11.8 recorded by binaural microphones.
READ FULL TEXT