Telepathy Labs, Inc.

Koninklijke Philips Corporation N.v.

Svox Ag

Martin Reber

Vijeta Avijeet

Piero Perucci

Johan Wouters

Stephen Brown

Josselyn Boudett

Jürgen Keller

Christof Traber

Marcel Riedi

A method, computer program product, and virtual agent system for an organization. The virtual agent system may include one or more processors and one or more memories configured to perform operations. The operations may include loading at least one model related to one or more processes of the organization where the model may be based on the structure information and one or more of procedures and protocols related to the organization. A process request, related to the at least one or more processes of the organization, from a user of the organization, may be received and analyzed.

Virtual agent system and method for modelling organization processes therefor

A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signal.

Artificial intelligence-based text-to-speech system and method

A method, computer program product, and computer system for text-to-speech synthesis is disclosed. Synthetic speech data for an input text may be generated. The synthetic speech data may be compared to recorded reference speech data corresponding to the input text. Based on, at least in part, the comparison of the synthetic speech data to the recorded reference speech data, at least one feature indicative of at least one difference between the synthetic speech data and the recorded reference speech data may be extracted. A speech gap filling model may be generated based on, at least in part, the at least one feature extracted. A speech output may be generated based on, at least in part, the speech gap filling model.

Text-to-speech synthesis system and method

An omni-channel, intelligent, proactive virtual agent system and method of use are provided by which a user may engage in a conversation with the agent to interact with structured and unstructured data of an enterprise that is stored in a domain-specific world model for the enterprise.

Omnichannel, intelligent, proactive virtual agent

A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signals.

A technique proves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. A back-end training system is configured to train the signal generation unit by applying psychoacoustic principles to improve quality of the generated audible speech signals.

A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. Speech signal specific modelling techniques in combination with applied psychoacoustic principles drive training efficiency of neural networks with positive impact on quality of generated speech signals.

An input linguistic description is converted into a speech waveform by deriving at least one target unit sequence corresponding to the linguistic description, selecting from a waveform unit database for the target unit sequences a plurality of alternative unit sequences approximating the target unit sequences, concatenating the alternative unit sequences to alternative speech waveforms and presenting the alternative speech waveforms to an operating person and enabling the choice of one of the presented alternative speech waveforms. There are no iterative cycles of manual modification and automatic selection, which enables a fast way of working. The operator does not need knowledge of units, targets, and costs, but chooses from a set of given alternatives. The fine-tuning of TTS prompts therefore becomes accessible to non-experts.

Text to speech synthesis

The invention provides an amplifier circuit made by digital CMOS processes, the amplifier circuit comprising a main operational amplifier with at least one input and at least one output and a feedback loop including a non-linear gateoxide capacitor, wherein a voltage control means is connected to the main operational amplifier to provide a voltage difference between the output common mode voltage and the input common mode voltage of the main operational amplifier to apply a DC biasing voltage across the non-linear gateoxide capacitor sufficient to operate the non-linear gateoxide capacitor in a bias range where the capacity of the none-linear gateoxide capacitor is almost independent of the applied voltage comprising the bias voltage plus a signal voltage.

Linear amplifier using non-linear CMOS capacitors

The invention relates to an operational amplifier comprising a first transistor amplifier stage at an input of the operational amplifier, which first transistor amplifier stage comprises chopped transistors, a second transistor amplifier stage cascoded to the first transistor amplifier stage, which second transistor amplifier stage is connected between the chopped first transistor amplifier stage and a supply voltage source, wherein the gain at the output of the chopped first transistor amplifier stage is reduced to g /g , where g *Rc is the gain of the first transistor amplifier stage, g *Rc is the gain of the second transistor amplifier stage and Rc is the resistance of the resistor between an output of the operational amplifier and the supply voltage source. An operational amplifier circuit comprises a main operational amplifier as specified above and feedback loops including capacitors between the inputs and outputs of the operational amplifier to form an integrator circuit or a filter circuit.

Operational amplifier with chopped input transistor pair

A digital communication device having a dual conversion architecture. A first rf-mixing stage is provided followed by a second, quadrature, mixing stage of which output signals are sampled by means of an analog-to-digital converter and supplied to a digital signal processor (DSP) for further baseband processing. The A/D converter is a modified sigma delta analog-to-digital converter. A mixing function is added to the A/D-conversion function by modifying the input stage of a conventional sigma delta bitstream A/D converter. The result is a reduced number of IC-external components and a reduced power consumption.

Growing community of inventors

Remetschwil, Switzerland

Martin Reber