User-modified speech output in a vehicle

Patent metadata

Field	Value
Publication number	US-2016267901-A1
Application number	US-201514643701-A
Country	US
Kind code	A1
Filing date	Mar 10, 2015
Priority date	Mar 10, 2015
Publication date	Sep 15, 2016
Grant date	—

Abstract

A system and method of controlling machine-generated speech in a vehicle includes: receiving a machine-generated voice selection from a vehicle occupant; accessing the machine-generated voice at the vehicle based on the selection; converting text to speech based on the machine-generated voice; and generating the speech through a vehicle audio system using the machine-generated voice selection.

First claim

1 . A method of controlling machine-generated speech in a vehicle, comprising the steps of:
(a) receiving a machine-generated voice selection made by a vehicle occupant; (b) accessing a machine-generated voice at the vehicle based on the selection; (c) receiving text to be converted to speech using the machine-generated voice; (d) converting the text to speech based on the machine-generated voice; and (e) generating the speech through a vehicle audio system using the machine-generated voice.

2 . The method of claim 1 , further comprising the step of presenting the machine-generated voice selection to the vehicle occupant based on vehicle location.

3 . The method of claim 1 , wherein the machine-generated voice further comprises pre-recorded speech.

4 . The method of claim 1 , wherein the machine-generated voice further comprises one or more phonemes or subwords.

5 . The method of claim 1 , wherein the machine-generated voice is based on a cartoon.

6 . The method of claim 1 , further comprising the step of receiving the text from the vehicle occupant.

7 . The method of claim 1 , further comprising the steps of: receiving speech from the vehicle occupant and converting the received speech to the text.

8 . The method of claim 1 , further comprising the steps of: receiving a speech speed selection from the vehicle occupant and increasing or decreasing the speed of the generated speech based on the received speed selection.

9 . A method of controlling machine-generated speech in a vehicle, comprising the steps of:
(a) receiving a machine-generated voice selection made by a vehicle occupant; (b) receiving speech from a vehicle occupant at an automatic speech recognition (ASR) system; (c) converting the received speech to text using the ASR system; (d) receiving the text at a text-to-speech (TTS) system; (e) accessing a machine-generated voice at the TTS system; and (f) generating speech through a vehicle audio system using the machine-generated voice.

10 . The method of claim 9 , further comprising the step of presenting the machine-generated voice selection to the vehicle occupant based on vehicle location.

11 . The method of claim 9 , wherein the machine-generated voice further comprises pre-recorded speech used by the TTS system.

12 . The method of claim 9 , wherein the machine-generated voice further comprises one or more phonemes or subwords used by the TTS system.

13 . The method of claim 9 , wherein the machine-generated voice is based on a cartoon.

14 . The method of claim 9 , further comprising the steps of: receiving a speech speed selection from the vehicle occupant and increasing or decreasing the speed of the generated speech based on the received speed selection.

15 . A method of controlling machine-generated speech in a vehicle, comprising the steps of:
(a) receiving a speech speed selection made by a vehicle occupant at the vehicle; (b) receiving speech from the vehicle occupant; (c) increasing or decreasing the speed of the received speech based on the received speed selection; and (d) generating modified speech through a vehicle audio system at the increased or decreased speed.

Assignees

• Gm Global Tech Operations Llc

Inventors

• Zhao Xufang
• Shahmurad Bassam S
• Malka Ilan

Classifications

• G10L13/00 Primary

  Speech synthesis; Text to speech systems · CPC title

• G10L21/043 Primary

  by changing speed · CPC title

• G10L13/027

  Concept to speech synthesisers; Generation of natural phrases from machine-based concepts (generation of parameters for speech synthesis out of text G10L13/08) · CPC title

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title