Patents by Inventor Ladan GOLIPOUR
Ladan GOLIPOUR has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20230134970Abstract: Systems and processes for generating audio books from text are provided. An example process includes, at an electronic device having one or more processors and memory: receiving a text including at least a first subset and a second subset, wherein at least a portion of the first subset overlaps with at least a portion of the second subset; determining, based on the text, a prosody for a speech output, wherein the prosody is representative of a genre; determining a semantic meaning of the text; and generating, based on the prosody and the semantic meaning, the speech output of the text.Type: ApplicationFiled: October 31, 2022Publication date: May 4, 2023Inventors: Ramya RASIPURAM, William BECKMAN, Ladan GOLIPOUR, David A. WINARSKY, Cheng-Chieh YEH, Weicheng ZHANG
-
Publication number: 20210272549Abstract: A system, method and computer-readable storage devices are for normalizing text for ASR and TTS in a language-neutral way. The system described herein divides Unicode text into meaningful chunks called “atomic tokens.” The atomic tokens strongly correlate to their actual pronunciation, and not to their meaning. The system combines the tokenization with a data-driven classification scheme, followed by class-determined actions to convert text to normalized form. The classification labels are based on pronunciation, unlike alternative approaches that typically employ Named Entity-based categories. Thus, this approach is relatively simple to adapt to new languages. Non-experts can easily annotate training data because the tokens are based on pronunciation alone.Type: ApplicationFiled: May 3, 2021Publication date: September 2, 2021Inventors: Ladan Golipour, Alistair D. Conkie
-
Patent number: 11049491Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.Type: GrantFiled: March 24, 2020Date of Patent: June 29, 2021Assignee: AT&T Intellectual Property I, L.P.Inventors: Alistair D. Conkie, Ladan Golipour, Ann K. Syrdal
-
Patent number: 10997964Abstract: A system, method and computer-readable storage devices are for normalizing text for ASR and TTS in a language-neutral way. The system described herein divides Unicode text into meaningful chunks called “atomic tokens.” The atomic tokens strongly correlate to their actual pronunciation, and not to their meaning. The system combines the tokenization with a data-driven classification scheme, followed by class-determined actions to convert text to normalized form. The classification labels are based on pronunciation, unlike alternative approaches that typically employ Named Entity-based categories. Thus, this approach is relatively simple to adapt to new languages. Non-experts can easily annotate training data because the tokens are based on pronunciation alone.Type: GrantFiled: August 16, 2019Date of Patent: May 4, 2021Assignee: AT&T INTELLECTUAL PROPERTY 1, L.P.Inventors: Ladan Golipour, Alistair D. Conkie
-
Publication number: 20200227023Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.Type: ApplicationFiled: March 24, 2020Publication date: July 16, 2020Inventors: Alistair D. Conkie, Ladan Golipour, Ann K. Syrdal
-
Patent number: 10607594Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.Type: GrantFiled: March 29, 2019Date of Patent: March 31, 2020Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.Inventors: Alistair D. Conkie, Ladan Golipour, Ann K. Syrdal
-
Publication number: 20190371294Abstract: A system, method and computer-readable storage devices are for normalizing text for ASR and TTS in a language-neutral way. The system described herein divides Unicode text into meaningful chunks called “atomic tokens.” The atomic tokens strongly correlate to their actual pronunciation, and not to their meaning. The system combines the tokenization with a data-driven classification scheme, followed by class-determined actions to convert text to normalized form. The classification labels are based on pronunciation, unlike alternative approaches that typically employ Named Entity-based categories. Thus, this approach is relatively simple to adapt to new languages. Non-experts can easily annotate training data because the tokens are based on pronunciation alone.Type: ApplicationFiled: August 16, 2019Publication date: December 5, 2019Inventors: Ladan GOLIPOUR, Alistair D. CONKIE
-
Patent number: 10395654Abstract: Systems and processes for operating an intelligent automated assistant to perform text-to-speech conversion are provided. An example method includes, at an electronic device having one or more processors, receiving a text corpus comprising unstructured natural language text. The method further includes generating a sequence of normalized text based on the received text corpus; and generating a pronunciation sequence representing the sequence of the normalized text. The method further includes causing an audio output to be provided to the user based on the pronunciation sequence. At least one of the sequence of normalized text and the pronunciation sequence is generated based on a data-driven learning network.Type: GrantFiled: August 10, 2017Date of Patent: August 27, 2019Assignee: Apple Inc.Inventors: Ladan Golipour, Matthias Neeracher, Ramya Rasipuram
-
Patent number: 10388270Abstract: A system, method and computer-readable storage devices are for normalizing text for ASR and TTS in a language-neutral way. The system described herein divides Unicode text into meaningful chunks called “atomic tokens.” The atomic tokens strongly correlate to their actual pronunciation, and not to their meaning The system combines the tokenization with a data-driven classification scheme, followed by class-determined actions to convert text to normalized form. The classification labels are based on pronunciation, unlike alternative approaches that typically employ Named Entity-based categories. Thus, this approach is relatively simple to adapt to new languages. Non-experts can easily annotate training data because the tokens are based on pronunciation alone.Type: GrantFiled: November 5, 2014Date of Patent: August 20, 2019Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.Inventors: Ladan Golipour, Alistair D. Conkie
-
Publication number: 20190228761Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.Type: ApplicationFiled: March 29, 2019Publication date: July 25, 2019Inventors: Alistair D. Conkie, Ladan Golipour, Ann K. Syrdal
-
Patent number: 10249290Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.Type: GrantFiled: June 11, 2018Date of Patent: April 2, 2019Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.Inventors: Alistair D. Conkie, Ladan Golipour, Ann K. Syrdal
-
Patent number: 10199034Abstract: A system, method and computer-readable storage devices are for using a single set of normalization protocols and a single language lexica (or dictionary) for both TTS and ASR. The system receives input (which is either text to be converted to speech or ASR training text), then normalizes the input. The system produces, using the normalized input and a dictionary configured for both automatic speech recognition and text-to-speech processing, output which is either phonemes corresponding to the input or text corresponding to the input for training the ASR system. When the output is phonemes corresponding to the input, the system generates speech by performing prosody generation and unit selection synthesis using the phonemes. When the output is text corresponding to the input, the system trains both an acoustic model and a language model for use in future speech recognition.Type: GrantFiled: August 18, 2014Date of Patent: February 5, 2019Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.Inventors: Alistair D. Conkie, Ladan Golipour
-
Publication number: 20180330729Abstract: Systems and processes for operating an intelligent automated assistant to perform text-to-speech conversion are provided. An example method includes, at an electronic device having one or more processors, receiving a text corpus comprising unstructured natural language text. The method further includes generating a sequence of normalized text based on the received text corpus; and generating a pronunciation sequence representing the sequence of the normalized text. The method further includes causing an audio output to be provided to the user based on the pronunciation sequence. At least one of the sequence of normalized text and the pronunciation sequence is generated based on a data-driven learning network.Type: ApplicationFiled: August 10, 2017Publication date: November 15, 2018Inventors: Ladan GOLIPOUR, Matthias NEERACHER, Ramya RASIPURAM
-
Publication number: 20180293972Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.Type: ApplicationFiled: June 11, 2018Publication date: October 11, 2018Inventors: Alistair D. CONKIE, Ladan GOLIPOUR, Ann K. SYRDAL
-
Patent number: 9997154Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.Type: GrantFiled: May 12, 2014Date of Patent: June 12, 2018Assignee: AT&T Intellectual Property I, L.P.Inventors: Alistair D. Conkie, Ladan Golipour, Ann K. Syrdal
-
Patent number: 9934775Abstract: Systems and processes for performing unit-selection text-to-speech synthesis are provided. In an example process, text to be converted to speech is received. The text is represented as a sequence of target units. A plurality of candidate speech segments corresponding to the sequence of target units are selected. Predicted statistical parameters of acoustic features associated with the sequence of target units are determined. The predicted statistical parameters of acoustic features are used to determine target costs and concatenation costs associated with the plurality of candidate speech segments. Based on a combined cost determined from the target costs and concatenation costs, a subset of candidate speech segments is selected from the plurality of candidate speech segments. Speech corresponding to the received text is generated using the subset of candidate speech segments.Type: GrantFiled: September 15, 2016Date of Patent: April 3, 2018Assignee: Apple Inc.Inventors: Tuomo J. Raitio, Kishore Sunkeswari Prahallad, Alistair D. Conkie, Ladan Golipour, David A. Winarsky
-
Publication number: 20170345411Abstract: Systems and processes for performing unit-selection text-to-speech synthesis are provided. In an example process, text to be converted to speech is received. The text is represented as a sequence of target units. A plurality of candidate speech segments corresponding to the sequence of target units are selected. Predicted statistical parameters of acoustic features associated with the sequence of target units are determined. The predicted statistical parameters of acoustic features are used to determine target costs and concatenation costs associated with the plurality of candidate speech segments. Based on a combined cost determined from the target costs and concatenation costs, a subset of candidate speech segments is selected from the plurality of candidate speech segments. Speech corresponding to the received text is generated using the subset of candidate speech segments.Type: ApplicationFiled: September 15, 2016Publication date: November 30, 2017Inventors: Tuomo J. RAITIO, Kishore Sunkeswari PRAHALLAD, Alistair D. CONKIE, Ladan GOLIPOUR, David A. WINARSKY
-
Publication number: 20160125872Abstract: A system, method and computer-readable storage devices are for normalizing text for ASR and TTS in a language-neutral way. The system described herein divides Unicode text into meaningful chunks called “atomic tokens.” The atomic tokens strongly correlate to their actual pronunciation, and not to their meaning The system combines the tokenization with a data-driven classification scheme, followed by class-determined actions to convert text to normalized form. The classification labels are based on pronunciation, unlike alternative approaches that typically employ Named Entity-based categories. Thus, this approach is relatively simple to adapt to new languages. Non-experts can easily annotate training data because the tokens are based on pronunciation alone.Type: ApplicationFiled: November 5, 2014Publication date: May 5, 2016Applicant: AT&T Intellectual Property I, L.P.Inventors: Ladan GOLIPOUR, Alistair D. CONKIE
-
Publication number: 20160049144Abstract: A system, method and computer-readable storage devices are for using a single set of normalization protocols and a single language lexica (or dictionary) for both TTS and ASR. The system receives input (which is either text to be converted to speech or ASR training text), then normalizes the input. The system produces, using the normalized input and a dictionary configured for both automatic speech recognition and text-to-speech processing, output which is either phonemes corresponding to the input or text corresponding to the input for training the ASR system. When the output is phonemes corresponding to the input, the system generates speech by performing prosody generation and unit selection synthesis using the phonemes. When the output is text corresponding to the input, the system trains both an acoustic model and a language model for use in future speech recognition.Type: ApplicationFiled: August 18, 2014Publication date: February 18, 2016Inventors: Alistair D. CONKIE, Ladan GOLIPOUR
-
Publication number: 20150325248Abstract: Systems, methods, and computer-readable storage devices to improve the quality of synthetic speech generation. A system selects speech units from a speech unit database, the speech units corresponding to text to be converted to speech. The system identifies a desired prosodic curve of speech produced from the selected speech units, and also identifies an actual prosodic curve of the speech units. The selected speech units are modified such that a new prosodic curve of the modified speech units matches the desired prosodic curve. The system stores the modified speech units into the speech unit database for use in generating future speech, thereby increasing the prosodic coverage of the database with the expectation of improving the output quality.Type: ApplicationFiled: May 12, 2014Publication date: November 12, 2015Applicant: AT&T Intellectual Property I, L.P.Inventors: Alistair D. CONKIE, Ladan GOLIPOUR, Ann K. SYRDAL