Tone Recognition Using Lifters and CTC
This work addresses the problem of accurate tone recognition for tonal language speakers, but it is incremental as it builds on established methods like CTC and CNNs.
The paper tackles tone recognition in continuous speech for tonal languages by using cepstrogram conversion, CNN feature extraction, and CTC prediction, achieving a lower tone error rate than existing techniques on the AISHELL-1 Mandarin corpus.
In this paper, we present a new method for recognizing tones in continuous speech for tonal languages. The method works by converting the speech signal to a cepstrogram, extracting a sequence of cepstral features using a convolutional neural network, and predicting the underlying sequence of tones using a connectionist temporal classification (CTC) network. The performance of the proposed method is evaluated on a freely available Mandarin Chinese speech corpus, AISHELL-1, and is shown to outperform the existing techniques in the literature in terms of tone error rate (TER).