44results about How to "Natural sound" patented technology

A speech synthesis system in a preferred embodiment includes a speech unit storage section, a phonetic environment storage section, a phonetic sequence / prosodic information input section, a plural-speech-unit selection section, a fused-speech-unit sequence generation section, and a fused-speech-unit modification / concatenation section. By fusing a plurality of selected speech units in the fused speech unit sequence generation section, a fused speech unit is generated. In the fused speech unit sequence generation section, the average power information is calculated for a plurality of selected M speech units, N speech units are fused together, and the power information of the fused speech unit is so corrected as to be equalized with the average power information of the M speech units.

Variation over time in fundamental frequency in singing voices is separated into a melody-dependent component and a phoneme-dependent component, modeled for each of the components and stored into a singing synthesizing database. In execution of singing synthesis, a pitch curve indicative of variation over time in fundamental frequency of the melody is synthesized in accordance with an arrangement of notes represented by a singing synthesizing score and the melody-dependent component, and the pitch curve is corrected, for each of pitch curve sections corresponding to phonemes constituting lyrics, using a phoneme-dependent component model corresponding to the phoneme. Such arrangements can accurately model a singing expression, unique to a singing person and appearing in a melody singing style of the person, while taking into account phoneme-dependent pitch variation, and thereby permits synthesis of singing voices that sound more natural.

A system for actively damping the low-frequency coloration of sound in a listening room is provided comprising an acoustic wave sensor, an acoustic wave actuator, and an electronic feedback controller. The listening room defines at least one mode of low-frequency coloration. The acoustic wave actuator is substantially collocated with the acoustic wave sensor within the listening room. The electronic feedback controller is operative to generate a signal at its output by applying a feedback controller transfer function. The feedback controller transfer function comprises a second order differential equation including a first variable representing a predetermined damping ratio and a second variable representing a tuned natural frequency and creates a 90 degree phase lead substantially at the resonant frequencies of at least one mode of low-frequency coloration. The feedback controller output signal represents a rate of change of volume velocity to be produced by the acoustic wave actuator. Further provided are methods for actively damping the low-frequency coloration of sound within a listening room and systems for actively treating noise within a fluid-carrying duct, including those which employ active low- and high-pass acoustic filters.

The invention relates to an audio editing method and apparatus, an electronic device and a storage medium. The method comprises steps of obtaining a modified text obtained by modifying an original text of a known to-be-edited audio according to a known modification text; predicting an audio duration corresponding to the modified text; adjusting a to-be-edited area of the to-be-edited audio according to the audio duration corresponding to the modified text to obtain an adjusted to-be-edited audio; on the basis of the pre-trained audio editing model, the edited audio being obtained according to the adjusted to-be-edited audio and the modified text, the edited audio obtained through the audio editing model is natural in context listening feeling, and the function of synthesizing new words not appearing in a corpus is supported.