Google LLC (20240331681). AUTOMATIC ADAPTATION OF THE SYNTHESIZED SPEECH OUTPUT OF A TRANSLATION APPLICATION simplified abstract
Contents
AUTOMATIC ADAPTATION OF THE SYNTHESIZED SPEECH OUTPUT OF A TRANSLATION APPLICATION
Organization Name
Inventor(s)
Rakesh Iyer of Santa Clara CA (US)
Jeffrey Robert Pitman of Santa Clara CA (US)
Pendar Yousefi of Santa Clara CA (US)
Tiruvilwamalai Raman of San Jose CA (US)
AUTOMATIC ADAPTATION OF THE SYNTHESIZED SPEECH OUTPUT OF A TRANSLATION APPLICATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240331681 titled 'AUTOMATIC ADAPTATION OF THE SYNTHESIZED SPEECH OUTPUT OF A TRANSLATION APPLICATION
Simplified Explanation: This patent application describes a system that can automatically adapt a computer-generated voice to sound similar to a user's voice by analyzing pitch characteristics.
- The system processes audio data of a user's spoken utterance to identify the frequency range of the user's voice.
- It can also compare the user's voice with a set of candidate computer-generated voices to select the most suitable one.
- The selected computer-generated voice is then modified based on the user's pitch characteristics to match the frequency range of the user's voice.
Key Features and Innovation:
- Automatic adaptation of computer-generated voices to match a user's voice.
- Analysis of pitch characteristics to identify the frequency range of a user's voice.
- Selection of a suitable computer-generated voice based on the user's voice.
- Modification of the selected voice to match the user's voice frequency range.
Potential Applications: This technology can be used in voice assistants, customer service bots, and other applications where personalized interactions are desired.
Problems Solved:
- Lack of personalized voice interactions in computer-generated voices.
- Difficulty in matching a computer-generated voice to a user's voice.
Benefits:
- Enhanced user experience with personalized voice interactions.
- Improved communication and engagement in human-computer interactions.
Commercial Applications: Potential commercial applications include voice-controlled devices, virtual assistants, and call center automation systems.
Questions about the Technology: 1. How does the system analyze pitch characteristics to match a user's voice? 2. What are the limitations of adapting computer-generated voices to sound like a user's voice?
By providing a detailed and informative overview of this technology, this article aims to educate readers about the innovative system of adapting computer-generated voices to match a user's voice.
Original Abstract Submitted
a computer generated voice can automatically be adapted to be similar to a user's voice. various implementations include processing audio data capturing a first language spoken utterance to identify one or more pitch characteristics. for example, the one or more pitch characteristics can include an estimated frequency range of the given user's voice. additionally or alternatively, the system can process the audio data capturing the first language spoken utterance and a set of candidate computer generated voices using a computer generated voice selection model to select a candidate computer generated voice. various implementations can include automatically modifying the selected candidate computer generated voice based on the one or more pitch characteristics to change the frequency range of the modified computer generated voice based on the user's voice.
