A method for training a speech recognition model includes obtaining sample utterances of synthesized speech in a target domain, obtaining transcribed utterances of non-synthetic speech in the target domain, and pre-training the speech recognition model on the sample utterances of synthesized speech in the target domain to attain an initial state for warm-start training. After pre-training the speech recognition model, the method also includes warm-start training the speech recognition model on the transcribed utterances of non-synthetic speech in the target domain to teach the speech recognition model to learn to recognize real/human speech in the target domain.

A method for training a speech recognition model includes obtaining sample utterances of synthesized speech in a target domain, obtaining transcribed utterances of non-synthetic speech in the target domain, and pre-training the speech recognition model on the sample utterances of synthesized speech in the target domain to attain an initial state for warm-start training. After pre-training the speech recognition model, the method also includes warm-start training the speech recognition model on the transcribed utterances of non-synthetic speech in the target domain to teach the speech recognition model to learn to recognize real/human speech in the target domain.

An audio processing method applied to a first terminal is described, and includes: in response to receiving of audio data input by a user at the first terminal, and determination that a voice change function is turned on, determining change parameters; and based on the change parameters, performing change processing on the audio data.

An audio processing method applied to a first terminal is described, and includes: in response to receiving of audio data input by a user at the first terminal, and determination that a voice change function is turned on, determining change parameters; and based on the change parameters, performing change processing on the audio data.

The present invention provides a voice conversion apparatus and the like using a differential spectral method which is capable of implementing both high voice quality and real-time performance even in wideband. A voice conversion apparatus 10 includes: an acquiring unit 11 configured to acquire a signal of a voice of a subject; a dividing unit 12 configured to divide the signal into sub-band signals corresponding to a plurality of frequency bands; a converting unit configured to convert one or a plurality of sub-band signals corresponding to one or a plurality of lower frequency bands, out of the sub-band signals corresponding to the plurality of frequency bands; and a synthesizing unit 16 configured to generate a synthesized voice by synthesizing the one or plurality of sub-band signals after conversion and the remaining sub-band signals that are not converted.

In some embodiments, a pitch filter for filtering a preliminary audio signal generated from an audio bitstream is disclosed. The pitch filter has an operating mode selected from one of either: (i) an active mode where the preliminary audio signal is filtered using filtering information to obtain a filtered audio signal, and (ii) an inactive mode where the pitch filter is disabled. The preliminary audio signal is generated in an audio encoder or audio decoder having a coding mode selected from at least two distinct coding modes, and the pitch filter is capable of being selectively operated in either the active mode or the inactive mode while operating in the coding mode based on control information.

In some embodiments, a pitch filter for filtering a preliminary audio signal generated from an audio bitstream is disclosed. The pitch filter has an operating mode selected from one of either: (i) an active mode where the preliminary audio signal is filtered using filtering information to obtain a filtered audio signal, and (ii) an inactive mode where the pitch filter is disabled. The preliminary audio signal is generated in an audio encoder or audio decoder having a coding mode selected from at least two distinct coding modes, and the pitch filter is capable of being selectively operated in either the active mode or the inactive mode while operating in the coding mode based on control information.

An adjustment method of sound output is disclosed. The adjustment method includes the following steps of: receiving an audio message having a vowel message; determining whether the audio message is a whispered voice message; if the audio message is a whispered voice message, outputting a normal voice message, wherein the spoken content of the normal voice message is the same as that of the audio message, and the normal voice message has a normal voice vowel message, wherein the sound energy of the low-frequency part of the normal voice vowel message is 1.5-1,000,000 times that of the vowel message.

An adjustment method of sound output is disclosed. The adjustment method includes the following steps of: receiving an audio message having a vowel message; determining whether the audio message is a whispered voice message; if the audio message is a whispered voice message, outputting a normal voice message, wherein the spoken content of the normal voice message is the same as that of the audio message, and the normal voice message has a normal voice vowel message, wherein the sound energy of the low-frequency part of the normal voice vowel message is 1.5-1,000,000 times that of the vowel message.

A voice morphing apparatus having adjustable parameters is described. The disclosed system and method include a voice morphing apparatus that morphs input audio to mask a speaker's identity. Parameter adjustment uses evaluation of an objective function that is based on the input audio and output of the voice morphing apparatus. The voice morphing apparatus includes objectives that are based adversarially on speaker identification and positively on audio fidelity. Thus, the voice morphing apparatus is adjusted to reduce identifiability of speakers while maintaining fidelity of the morphed audio. The voice morphing apparatus may be used as part of an automatic speech recognition system.