A text-to-speech synthesis method using machine learning, the text-to-speech synthesis method is disclosed. The method includes generating a single artificial neural network text-to-speech synthesis model by performing machine learning based on a plurality of learning texts and speech data corresponding to the plurality of learning texts, receiving an input text, receiving an articulatory feature of a speaker, generating output speech data for the input text reflecting the articulatory feature of the speaker by inputting the articulatory feature of the speaker to the single artificial neural network text-to-speech synthesis model.

A method includes receiving an input text utterance to be synthesized into expressive speech having an intended prosody and a target voice and generating, using a first text-to-speech (TTS) model, an intermediate synthesized speech representation for the input text utterance. The intermediate synthesized speech representation possesses the intended prosody. The method also includes providing the intermediate synthesized speech representation to a second TTS model that includes an encoder portion and a decoder portion. The encoder portion is configured to encode the intermediate synthesized speech representation into an utterance embedding that specifies the intended prosody. The decoder portion is configured to process the input text utterance and the utterance embedding to generate an output audio signal of expressive speech that has the intended prosody specified by the utterance embedding and speaker characteristics of the target voice.

A method includes receiving an input text utterance to be synthesized into expressive speech having an intended prosody and a target voice and generating, using a first text-to-speech (TTS) model, an intermediate synthesized speech representation for the input text utterance. The intermediate synthesized speech representation possesses the intended prosody. The method also includes providing the intermediate synthesized speech representation to a second TTS model that includes an encoder portion and a decoder portion. The encoder portion is configured to encode the intermediate synthesized speech representation into an utterance embedding that specifies the intended prosody. The decoder portion is configured to process the input text utterance and the utterance embedding to generate an output audio signal of expressive speech that has the intended prosody specified by the utterance embedding and speaker characteristics of the target voice.

Processor(s) of a client device can: identify a textual segment stored locally at the client device; process the textual segment, using an on-device TTS generator model, to generate synthesized speech audio data that includes synthesized speech of the textual segment; process the synthesized speech, using an on-device ASR model to generate predicted ASR output; and generate a gradient based on comparing the predicted ASR output to ground truth output corresponding to the textual segment. Processor(s) of the client device can also: process the synthesized speech audio data using an on-device TTS generator model to make a prediction; and generate a gradient based on the prediction. In these implementations, the generated gradient(s) can be used to update weight(s) of the respective on-device model(s) and/or transmitted to a remote system for use in remote updating of respective global model(s). The updated weight(s) and/or the updated model(s) can be transmitted to client device(s).

Processor(s) of a client device can: identify a textual segment stored locally at the client device; process the textual segment, using an on-device TTS generator model, to generate synthesized speech audio data that includes synthesized speech of the textual segment; process the synthesized speech, using an on-device ASR model to generate predicted ASR output; and generate a gradient based on comparing the predicted ASR output to ground truth output corresponding to the textual segment. Processor(s) of the client device can also: process the synthesized speech audio data using an on-device TTS generator model to make a prediction; and generate a gradient based on the prediction. In these implementations, the generated gradient(s) can be used to update weight(s) of the respective on-device model(s) and/or transmitted to a remote system for use in remote updating of respective global model(s). The updated weight(s) and/or the updated model(s) can be transmitted to client device(s).

A method for providing sentiment analysis of a natural language service request to automatically identify and map a user state of mind by utilizing artificial intelligence is disclosed. The method includes receiving, via a graphical user interface, a raw input, the raw input including a computer file corresponding to a natural language request; parsing the raw input into component parts; annotating, by using a model, each of the component parts with a predetermined indicator, the predetermined indicator corresponding to the user state of mind; mapping, by using the model, the component parts based on the predetermined indicator; compiling the mapped component parts into a structured input, and determining, by using the model, a quality that corresponds to the structured input.

A method for providing sentiment analysis of a natural language service request to automatically identify and map a user state of mind by utilizing artificial intelligence is disclosed. The method includes receiving, via a graphical user interface, a raw input, the raw input including a computer file corresponding to a natural language request; parsing the raw input into component parts; annotating, by using a model, each of the component parts with a predetermined indicator, the predetermined indicator corresponding to the user state of mind; mapping, by using the model, the component parts based on the predetermined indicator; compiling the mapped component parts into a structured input, and determining, by using the model, a quality that corresponds to the structured input.

A method of providing a frame-based mel spectral representation of speech includes receiving a text utterance having at least one word and selecting a mel spectral embedding for the text utterance. Each word has at least one syllable and each syllable has at least one phoneme. For each phoneme, the method further includes using the selected mel spectral embedding to: (i) predict a duration of the corresponding phoneme based on corresponding linguistic features associated with the word that includes the corresponding phoneme and corresponding linguistic features associated with the syllable that includes the corresponding phoneme; and (ii) generate a plurality of fixed-length predicted mel-frequency spectrogram frames based on the predicted duration for the corresponding phoneme. Each fixed-length predicted mel-frequency spectrogram frame represents mel-spectral information of the corresponding phoneme.

A speech-processing system receives both text data and natural-understanding data (e.g., a domain, intent, and/or entity) related to a command represented in the text data. The system uses the natural-understanding data to vary vocal characteristics in determining spectrogram data corresponding to the text data based on the natural-understanding data.

A speech-processing system receives both text data and natural-understanding data (e.g., a domain, intent, and/or entity) related to a command represented in the text data. The system uses the natural-understanding data to vary vocal characteristics in determining spectrogram data corresponding to the text data based on the natural-understanding data.