37results about How to "Improve speech synthesis" patented technology

The invention provides a method and apparatus for generating a word segmentation dictionary and a method and apparatus for text to speech. The method for generating the word segmentation dictionary includes: dividing texts within a present range that has been collected and obtaining sentences which constitute the texts; dividing the sentences and obtaining character strings of different lengths; based on the character strings of different lengths, determining credible vocabulary entries within the character strings of different lengths; based on the credible vocabulary entries, establishing the word segmentation dictionary. The method for generating the word segmentation dictionary can obtain the word segmentation dictionary which fits a corresponding field, which can further increase the effect of word segmentation and the effect of text to speech.

The present disclosure provides a speech synthesis method, device, device, and medium, wherein the method includes: acquiring semantic features, phoneme features, and acoustic features of a target text; performing a first alignment operation on semantic features and acoustic features to obtain a first alignment result ; Perform a second alignment operation on the phoneme features and acoustic features to obtain a second alignment result; perform feature fusion according to the first alignment result and the second alignment result to obtain fusion features; generate a synthetic speech corresponding to the target text based on the fusion features. The present disclosure can better improve the speech synthesis effect.

The invention discloses a voice synthesis method and a device. The voice synthesis method comprises steps of performing text characteristic extraction on a text to be synthesized to obtain the context characteristic information, obtaining a pre-generated model, wherein the pre-generated model is generated by training according to the context characteristic information of the training sample and converted acoustic parameter, and the converted acoustic parameters comprise a plurality of rhythm level fundamental frequency parameters, determining the model output parameter corresponding to the context characteristic information according to the model, wherein the model output parameters comprise a plurality of the rhythm level fundamental frequency parameters, performing the fundamental frequency reconstruction on the plurality of rhythm level fundamental frequency parameter, and synthesizing voice according to the parameter after the fundamental frequency reconstruction and the other parameters in the model output parameters. The method can improve the performance result of the synthesized speech.

The embodiment of the present invention provides a speech synthesis model training method, speech synthesis method and device, the speech synthesis model training method includes: obtaining the first word vector sequence corresponding to the Chinese character sentence of encoding training; using the encoding module to encode the first word vector The sequence is encoded to obtain the first linguistic coding feature; the linguistic feature decoding module is used to decode the linguistic feature of the first linguistic coding feature to obtain the linguistic decoding feature; according to the relationship between the linguistic decoding feature and the reference linguistic decoding feature The linguistic feature loss of the speech synthesis model is adjusted by adjusting the model parameters of the coding module of the speech synthesis model until the linguistic feature loss meets the linguistic feature loss threshold, and the trained coding module of the speech synthesis model is obtained. The speech synthesis model training method, speech synthesis method and related devices provided by the embodiments of the present invention can reduce the complexity of speech synthesis, improve the training accuracy of the encoder, and ensure the effect of synthesized speech.