Text formatting from speech
AssigneeInternational Business Machines Corporation
InventorsRon Hoory, Alan Jay Wecker
Life of this patent
Estimating the term…
Abstract
A method for converting speech to text and vice versa. The method for converting speech to text includes receiving a spoken input having a non-verbal characteristic, and automatically generating a text output, responsive to the spoken input, having a variable format characteristic corresponding to the non-verbal characteristic of the spoken input. The method for converting text to speech includes receiving a text input having a given variable format characteristic and synthesizing speech corresponding to the text input and having a non-verbal characteristic corresponding to the variable format characteristic of the text input.
Claims11
A method for converting speech to text, comprising:
- receiving a spoken input having a non-verbal characteristic;
- and
- automatically generating a text output, responsive to the spoken input, having a variable font effect characteristic corresponding to the non-verbal characteristic of the spoken input,
- wherein receiving the spoken input comprises determining words and boundaries between words, and wherein generating the text output comprises generating text corresponding to the words,
- wherein receiving the spoken input comprises determining parts of words and boundaries between parts of words in the spoken input, and wherein the non-verbal characteristic comprises at least one characteristic of the parts of the words selected from a group consisting of a speed, a pitch, and a volume of the parts of the words.
A method for converting speech to text, comprising:
- receiving a spoken input having a non-verbal characteristic;
- and
- automatically generating a text output, responsive to the spoken input, having a variable font effect characteristic corresponding to the non-verbal characteristic of the spoken input,
- wherein generating the text output comprises generating the text output according to a predetermined mapping between the variable font effect characteristic and the non-verbal characteristic,
- wherein generating the text output comprises normalizing a distribution of the non-verbal characteristic over a predetermined quantity of speech according to an adaptive mapping.
A method for converting speech to text, comprising:
- receiving a spoken input having a non-verbal characteristic;
- and
- automatically generating a text output, responsive to the spoken input, having a variable font effect characteristic corresponding to the non-verbal characteristic of the spoken input,
- wherein generating the text output comprises generating the text output according to a predetermined mapping between the variable font effect characteristic and the non-verbal characteristic,
- wherein generating the text output according to the predetermined mapping comprises generating the text output according to a continuous mapping, wherein a range of values of the non-verbal characteristic is mapped to a range of values of the variable font effect characteristic.
A method for converting speech to text, comprising:
- receiving a spoken input having a non-verbal characteristic;
- and
- automatically generating a text output, responsive to the spoken input, having a variable font effect characteristic corresponding to the non-verbal characteristic of the spoken input,
- wherein generating the text output comprises generating the text output according to a predetermined mapping between the variable font effect characteristic and the non-verbal characteristic,
- wherein automatically generating the text output comprises:
- applying the predetermined mapping at a transmitter;
- encoding the text output with the variable font effect characteristic as a data bitstream at the transmitter
- transmitting the data bitstream from the transmitter to a receiver;
- and
- decoding the data bitstream to generate the text output with the variable font effect characteristic at the receiver.
A method for converting speech to text, comprising:
- receiving a spoken input having a non-verbal characteristic;
- and
- automatically generating a text output, responsive to the spoken input, having a variable font effect characteristic corresponding to the non-verbal characteristic of the spoken input,
- wherein generating the text output comprises generating the text output according to a predetermined mapping between the variable font effect characteristic and the non-verbal characteristic,
- wherein automatically generating the text output comprises:
- encoding the text output and the non-verbal characteristic as a data bitstream at a transmitter;
- transmitting the data bitstream from the transmitter to a receiver;
- decoding the data bitstream at the receiver;
- and
- applying the predetermined mapping at the receiver, responsive to the non-verbal characteristic encoded in the data bitstream, so as to generate the text output with the variable font effect characteristic.
A method for converting speech to text, comprising:
- receiving a spoken input having a non-verbal characteristic;
- and
- automatically generating a text output, responsive to the spoken input, having a variable font effect characteristic corresponding to the non-verbal characteristic of the spoken input,
- wherein generating the text output comprises generating a custom-built font for the text output, having one or more variable features used to express the non-verbal characteristic.
A speech/text processor, which is adapted to receive a spoken input having a non-verbal characteristic and to automatically generate a text output, responsive to the spoken input, having a variable font effect characteristic corresponding to the non-verbal characteristic of the spoken input,
- which further encodes as encoded text the text output with the variable font effect characteristic and transmits the encoded text to a receiver which decodes the encoded text.
A speech/text processor, which is adapted to receive a spoken input having a non-verbal characteristic and to automatically generate a text output, responsive to the spoken input, having a variable font effect characteristic corresponding to the non-verbal characteristic of the spoken input,
- and which is adapted to generate the text output according to a predetermined mapping between the variable font effect characteristic and the non-verbal characteristic,
- which further encodes as encoded text the text output and the non-verbal characteristic and transmits the encoded text to a receiver which decodes the encoded text and applies the predetermined mapping responsive to the non-verbal characteristic encoded in the encoded text.
A method for converting text to speech, comprising:
- receiving a text input having a given variable font effect characteristic;
- and
- synthesizing speech corresponding to the text input and having a non-verbal characteristic corresponding to the variable font effect characteristic of the text input,
- wherein receiving the text input comprises receiving the text input in a custom-built font having one or more variable features used to express the non-verbal characteristic.
Dependencies are inferred from the claim text.