A speech-processing system receives input data representing text. A first encoder processes segments of the text to determine embedding data representing the text, and a second encoder processes corresponding audio data to determine prosodic data corresponding to the text. The embedding and prosodic data is processed to create output data including a representation of speech corresponding to the text and prosody.

A reproduction control method implemented by a computer includes receiving, from a first terminal device, a first reproduction request in accordance with an instruction from a first user, receiving, from a second terminal device, a second reproduction request in accordance with an instruction from a second user, acquiring a first acoustic signal representing a first sound in accordance with the first reproduction request, and a second acoustic signal representing a second sound which is in accordance with the second reproduction request and have acoustic characteristics that differ from acoustic characteristics of the first sound represented by the first acoustic signal, mixing the first acoustic signal and the second acoustic signal, thereby generating a third acoustic signal, and causing a reproduction system to reproduce a third sound represented by the third acoustic signal.

Provided is a system which allows a learner who is a non-native speaker of a given language to intuitively improve pronunciation of the language. A pronunciation conversion apparatus includes a conversion section which converts a first feature value corresponding to a first speech signal obtained when a first speaker who speaks a given language as his/her native language speaks another language such that the first feature value approaches a second feature value corresponding to a second speech signal obtained when a second speaker who speaks the other language as his/her native language speaks the other language, each of the first feature value and the second feature value is a feature value capable of representing a difference in pronunciation, and a speech signal obtained from the first feature value after the conversion is presented to the first speaker.

A method and a system for generating an intelligent voice assistant response are provided. The method includes receiving a preliminary voice assistant response to a user command and determining a subjective polarity score of the preliminary voice assistant response and a dynamic polarity score indicative of an instant user reaction to the preliminary voice assistant response, once the preliminary voice assistant response is delivered. The method thereafter determines a sentiment score of the preliminary voice assistant response based on the subjective polarity score and the dynamic polarity score. The method identifies an emotionally uplifting information for the user that is to be combined with the preliminary voice assistant response. The method further includes generating a personalized note to be combined with the preliminary voice assistant response and generating the intelligent voice assistant response by combining the preliminary voice assistant response with the emotionally uplifting information and the personalized note.

This disclosure describes a system that analyzes a corpus of text (e.g., a financial article, an audio book, etc.) so that the context surrounding the text is fully understood. For instance, the context may be an environment described by the text, or an environment in which the text occurs. Based on the analysis, the system can determine sentiment, part of speech, entities, and/or human characters at the token level of the text, and automatically generate Speech Synthesis Markup Language (SSML) tags based on this information. The SSML tags can be used by applications, services, and/or features that implement text-to-speech (TTS) conversion to improve the audio experience for end-users. Consequently, via the techniques described herein, more realistic and human-like speech synthesis can be efficiently implemented at larger scale (e.g., for audio books, for all the articles published to a news site, etc.).

A speech to text system includes a text and labels module receiving a text input and providing a text analysis and a label with a phonetic description of the text. A label buffer receives the label from the text and labels module. A parameter generation module accesses the label from the label buffer and generates a speech generation parameter. A parameter buffer receives the parameter from the parameter generation module. An audio generation module receives the text input, the label, and/or the parameter and generates a plurality of audio samples, A scheduler monitors and schedules the text and label module, the parameter generation module, and/or the audio generation module. The parameter generation module is further configured to initialize a voice identifier with a Voice Style Sheet (VSS) parameter, receive an input indicating a modification to the VSS parameter, and modify the VSS parameter according to the modification.

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 lip language recognition method, applied to a mobile terminal having a sound mode and a silent mode, includes: training a deep neural network in the sound mode; collecting a user's lip images in the silent mode; and identifying content corresponding to the user's lip images with the deep neural network trained in the sound mode. The method further includes: switching from the sound mode to the silent mode when a privacy need of the user arises.

Voice synthesis method and apparatus generate second control data using an intermediate trained model with first input data including first control data designating phonetic identifiers, change the second control data in accordance with a first user instruction provided by a user, generate synthesis data representing frequency characteristics of a voice to be synthesized using a final trained model with final input data including the first control data and the changed second control data, and generate a voice signal based on the generated synthesis data.

Voice synthesis method and apparatus generate second control data using an intermediate trained model with first input data including first control data designating phonetic identifiers, change the second control data in accordance with a first user instruction provided by a user, generate synthesis data representing frequency characteristics of a voice to be synthesized using a final trained model with final input data including the first control data and the changed second control data, and generate a voice signal based on the generated synthesis data.