Journal Call no. | TA4.C3578 |
---|
Author | Liao, Yuan-Fu. |
---|
Article Title | An overview of RNN-based Mandarin speech recognition approaches / Yuan-Fu Liao ... [et al.]. |
---|
Is Part Of | Journal of the Chinese Institute of Engineers ; v.22, no.5, Sep 1999, p.535-547, illus. |
---|
Abstract | The artificial neural network (ANN)-based approach is an alternate to the hidden Markov model (HMM) method which is the currently dominant technology in the field of speech recognition. The article is an overview of the recurrent neural networks (RNN)-based approaches to Mandarin speech recognition. Some RNN-based approaches proposed previously: syllable-boundary pre-segmentation, broad-class pre-classification, prosodic phrase boundary detection, and isolated and continuous syllable recognitions are discussed. The study finds from the survey that these approaches are all effective. So the RNN technology is comparable to the conventional HMM method on Mandarin speech recognition. |
---|