At&t Intellectual Property I, L.p.

At+t Corp.

Nuance Communications, Inc.

Mark Charles Beutnagel

Alistair D Conkie

Michael Dennis Riley

Mehryar Mohri

Joern Ostermann

Yeon-Jun Kim

Horst Juergen Schroeter

Ann K Syrdal

Andrea Basso

Benjamin J Stern

Amanda Joy Stent

Taniya Mishra

Yao Rong Wang

Schuyler Reynier Quackenbush

David A Kapilow

Ioannis G Stylianou

Ariel Fischer

Systems, methods, and computer-readable storage media for intelligent caching of concatenative speech units for use in speech synthesis. A system configured to practice the method can identify speech units that are required for synthesizing speech. The system can request from a server the text-to-speech unit needed to synthesize the speech. The system can then synthesize speech using text-to-speech units already stored and a received text-to-speech unit from the server.

System and method for distributed voice models across cloud and device for embedded text-to-speech

A hybrid markup language document (or 'HMLD') is scanned for a partition boundary. Content in the HMLD that precedes the partition boundary is discarded for simpler and faster processing.

Partitioning of markup language documents

Systems, methods, and computer-readable storage media for intelligent caching of concatenative speech units for use in speech synthesis. A system configured to practice the method can identify, in a local cache of text-to-speech units for a text-to-speech voice an absent text-to-speech unit which is not in the local cache. The system can request from a server the absent text-to-speech unit. The system can then synthesize speech using the text-to-speech units and a received text-to-speech unit from the server.

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for detecting and correcting abnormal stress patterns in unit-selection speech synthesis. A system practicing the method detects incorrect stress patterns in selected acoustic units representing speech to be synthesized, and corrects the incorrect stress patterns in the selected acoustic units to yield corrected stress patterns. The system can further synthesize speech based on the corrected stress patterns. In one aspect, the system also classifies the incorrect stress patterns using a machine learning algorithm such as a classification and regression tree, adaptive boosting, support vector machine, and maximum entropy. In this way a text-to-speech unit selection speech synthesizer can produce more natural sounding speech with suitable stress patterns regardless of the stress of units in a unit selection database.

System and method for automatic detection of abnormal stress patterns in unit selection synthesis

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for reducing latency in web-browsing TTS systems without the use of a plug-in or Flash&#xae; module. A system configured according to the disclosed methods allows the browser to send prosodically meaningful sections of text to a web server. A TTS server then converts intonational phrases of the text into audio and responds to the browser with the audio file. The system saves the audio file in a cache, with the file indexed by a unique identifier. As the system continues converting text into speech, when identical text appears the system uses the cached audio corresponding to the identical text without the need for re-synthesis via the TTS server.

System and method for low-latency web-based text-to-speech without plugins

A speech synthesis process can record concatenation costs of unit sequential pairs to a concatenation cost database for speech synthesis by synthesizing speech from a text, identifying an acoustic unit sequential pair in the speech, searching for a concatenation cost for the acoustic unit sequential pair in a database using a hash table for the database, and when the concatenation cost is not found in the database, assigning a default value as the concatenation cost for the acoustic unit sequential pair.

Concatenation cost in speech synthesis for acoustic unit sequential pair using hash table and default concatenation cost

Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for unit selection synthesis. The method causes a computing device to add a supplemental phoneset to a speech synthesizer front end having an existing phoneset, modify a unit preselection process based on the supplemental phoneset, preselect units from the supplemental phoneset and the existing phoneset based on the modified unit preselection process, and generate speech based on the preselected units. The supplemental phoneset can be a variation of the existing phoneset, can include a word boundary feature, can include a cluster feature where initial consonant clusters and some word boundaries are marked with diacritics, can include a function word feature which marks units as originating from a function word or a content word, and/or can include a pre-vocalic or post-vocalic feature. The speech synthesizer front end can incorporates the supplemental phoneset as an extra feature.

System and method for generalized preselection for unit selection synthesis

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating speech. One variation of the method is from a server side, and another variation of the method is from a client side. The server side method, as implemented by a network-based automatic speech processing system, includes first receiving, from a network client independent of knowledge of internal operations of the system, a request to generate a text-to-speech voice. The request can include speech samples, transcriptions of the speech samples, and metadata describing the speech samples. The system extracts sound units from the speech samples based on the transcriptions and generates an interactive demonstration of the text-to-speech voice based on the sound units, the transcriptions, and the metadata, wherein the interactive demonstration hides a back end processing implementation from the network client. The system provides access to the interactive demonstration to the network client.

System and method for cloud-based text-to-speech web services

A speech synthesis system can record concatenation costs of most common acoustic unit sequential pairs to a concatenation cost database for speech synthesis by synthesizing speech from a text, identifying a most common acoustic unit sequential pair in the speech, assigning a concatenation cost to the most common acoustic sequential pair, and recording the concatenation cost of the most common acoustic sequential pair to a concatenation cost database.

Recording concatenation costs of most common acoustic unit sequential pairs to a concatenation cost database for speech synthesis

Systems, methods, and computer-readable storage media for intelligent caching of concatenative speech units for use in speech synthesis. A system configured to practice the method can identify a speech synthesis context, and determine, based on a local cache of text-to-speech units for a text-to-speech voice and based on the speech synthesis context, additional text-to-speech units which are not in the local cache. The system can request from a server the additional text-to-speech units, and store the additional text-to-speech units in the local cache. The system can then synthesize speech using the text-to-speech units and the additional text-to-speech units in the local cache. The system can prune the cache as the context changes, based on availability of local storage, or after synthesizing the speech. The local cache can store a core set of text-to-speech units associated with the text-to-speech voice that cannot be pruned from the local cache.

Growing community of inventors

Mendham, NJ, United States of America

Mark Charles Beutnagel