full transcript
From the Ted Talk by Rupal Patel: Synthetic voices, as unique as fingerprints
Unscramble the Blue Letters
So once you have that in mind, how do you go about bnidulig this voice? Well, you have to find someone who is willing to be a sotgarure. It's not such an ominous thing. Being a surrogate donor only requires you to say a few hundred to a few thousand utterances. The process goes something like this.
(Video) Voice: Things happen in pairs.
I love to sleep.
The sky is blue without clouds.
RP: Now she's going to go on like this for about three to four hruos, and the idea is not for her to say everything that the target is going to want to say, but the idea is to cover all the different combinations of the sounds that ouccr in the language. The more speech you have, the better sounding voice you're going to have. Once you have those recordings, what we need to do is we have to parse these recordings into little stieppns of speech, one- or two-sound combinations, sometimes even whole words that srtat pponaiutlg a dtaseat or a database. We're going to call this database a voice bank. Now the power of the voice bank is that from this voice bank, we can now say any new utterance, like, "I love chocolate" — everyone needs to be able to say that— fish through that database and find all the senegmts necessary to say that utterance.
Open Cloze
So once you have that in mind, how do you go about ________ this voice? Well, you have to find someone who is willing to be a _________. It's not such an ominous thing. Being a surrogate donor only requires you to say a few hundred to a few thousand utterances. The process goes something like this.
(Video) Voice: Things happen in pairs.
I love to sleep.
The sky is blue without clouds.
RP: Now she's going to go on like this for about three to four _____, and the idea is not for her to say everything that the target is going to want to say, but the idea is to cover all the different combinations of the sounds that _____ in the language. The more speech you have, the better sounding voice you're going to have. Once you have those recordings, what we need to do is we have to parse these recordings into little ________ of speech, one- or two-sound combinations, sometimes even whole words that _____ __________ a _______ or a database. We're going to call this database a voice bank. Now the power of the voice bank is that from this voice bank, we can now say any new utterance, like, "I love chocolate" — everyone needs to be able to say that— fish through that database and find all the ________ necessary to say that utterance.
Solution
- hours
- surrogate
- building
- snippets
- segments
- populating
- occur
- dataset
- start
Original Text
So once you have that in mind, how do you go about building this voice? Well, you have to find someone who is willing to be a surrogate. It's not such an ominous thing. Being a surrogate donor only requires you to say a few hundred to a few thousand utterances. The process goes something like this.
(Video) Voice: Things happen in pairs.
I love to sleep.
The sky is blue without clouds.
RP: Now she's going to go on like this for about three to four hours, and the idea is not for her to say everything that the target is going to want to say, but the idea is to cover all the different combinations of the sounds that occur in the language. The more speech you have, the better sounding voice you're going to have. Once you have those recordings, what we need to do is we have to parse these recordings into little snippets of speech, one- or two-sound combinations, sometimes even whole words that start populating a dataset or a database. We're going to call this database a voice bank. Now the power of the voice bank is that from this voice bank, we can now say any new utterance, like, "I love chocolate" — everyone needs to be able to say that— fish through that database and find all the segments necessary to say that utterance.
Frequently Occurring Word Combinations
ngrams of length 2
collocation |
frequency |
unique vocal |
3 |
grown man |
2 |
severe speech |
2 |
vocal identities |
2 |
personalized voices |
2 |
vocal identity |
2 |
source characteristics |
2 |
voice bank |
2 |
ngrams of length 3
collocation |
frequency |
unique vocal identities |
2 |
Important Words
- bank
- blue
- building
- call
- clouds
- combinations
- cover
- database
- dataset
- donor
- find
- fish
- happen
- hours
- idea
- language
- love
- mind
- occur
- ominous
- pairs
- parse
- populating
- power
- process
- recordings
- requires
- segments
- sky
- sleep
- snippets
- sounding
- sounds
- speech
- start
- surrogate
- target
- thousand
- utterance
- utterances
- video
- voice
- words