2results about How to "Improve speech synthesis" patented technology

This application discloses a speech synthesis method, apparatus, device, and storage medium. The method involves analyzing the original text to be synthesized to obtain a phoneme sequence; inputting the phoneme sequence into a configured speech synthesis model to obtain synthesized speech output by the model. The speech synthesis model is a final speech synthesis model after parameter adjustment of the basic speech synthesis model, using the scoring results of multiple candidate speech samples corresponding to the input test text synthesized by the basic speech synthesis model as reward signals. The scoring results of each candidate speech sample conform to the user's auditory perception goals. This application adds user auditory feedback signals (i.e., the scoring results as reward signals) to the training process of the speech synthesis model, guiding the speech synthesis model to optimize model parameters in a direction that better conforms to the user's auditory perception, making the synthesized speech more in line with the user's auditory perception goals and improving the speech synthesis effect.

This invention, based on decoding research in speech brain-computer interfaces, discloses a discrete decoding method guided by continuous decoding in speech brain-computer interfaces. This method utilizes a deep learning model where continuous and discrete decoding systems coexist. First, it trains the continuous decoding system on information such as Mel spectrum, fundamental frequency, and non-periodic signals from the acoustic data. Then, it uses the features extracted from the continuous decoding to guide the discrete decoding system through transfer learning, ultimately completing the training of the discrete decoding system (i.e., the classification task). The performance of this discrete decoding is significantly higher than that of simple discrete decoding. Furthermore, the fundamental frequency and other signals output by the trained continuous decoding system can be used as adjustment inputs for subsequent speech synthesis systems based on the discrete decoding results, enhancing the speech synthesis effect of the discrete decoding results.