3 results about "Speech synthesis" patented technology

A system for synthesising expressive speech includes: an interface configured to receive an input text for conversion to speech; a memory; and at least one processor coupled to the memory. The processor is configured to generate, using an expressivity characterisation module, a plurality of expression vectors, wherein each expression vector is a representation of prosodic information in a reference audio style file, and synthesise expressive speech from the input text, using an expressive acoustic model comprising a deep convolutional neural network that is conditioned by at least one of the plurality of expression vectors.

The invention discloses a pickup and noise reduction method for a built-in earphone of a transmitting pickup microphone, and belongs to the technical field of earphones. According to the a built-in earphone of a transmitting pickup microphone, the transmitting and pickup microphone is arranged in an independent sealed cavity in the inner wall of the earphone, and the pickup and noise reduction method specifically comprises the following steps: (1) preprocessing a voice signal, including anti-aliasing, A/D conversion, pre-emphasis and central wave elimination processes; (2) channel mapping processing, including four stages of LPC-based feature extraction, channel mapping, speech synthesis and de-emphasis; and (3) voice focusing enhancement processing, wherein the voice focusing enhancementprocessing comprises power spectrum estimation and amplitude attenuation processing, voice centering, high-pass filtering, high-frequency enhancement, dynamic compression and later-stage enhancement processing, and pickup and noise reduction are realized. According to the pickup and noise reduction method disclosed by the invention, the definition, intelligibility and the like of voice transmission on a full frequency band are obviously enhanced; AND the structure is simple and the cost is low.

The invention discloses a speech synthesis method capable of being used for a chip end. The speech synthesis method comprises the following steps: step 1, calculating a pulse excitation seed signal and a noise excitation seed signal; step 2, solving an excitation signal according to the fundamental frequency F0 of the given voice and the band-shaped aperiodic ratio ap; and step 3, for each frame of frequency spectrum envelope of the given audio, calculating corresponding audio data, and then performing superposition according to frame shift to obtain a final voice waveform. According to the method, the required pulse excitation seed signal is calculated off line in advance, only multiplication and addition operation is performed when periodic excitation and non-periodic excitation are calculated, Fourier transform and inverse Fourier transform are not involved, and the operation speed of the vocoder at a chip end is increased.