Speech Research Lab: Speech Synthesis, Speech Recognition, and Speech Processing

AITopics Original Links

The ModelTalker TTS system converts plain English text to speech. It uses a text to phoneme system which includes capabilities for parsing ToBI-like descriptions of the intonation. Synthesis is accomplished through a combination of database-driven speech and a variant on diphone-based phoneme to sound engines known as Biphone-Constrained Concatenation (BCC). Speech stored in the database encompasses common words and phrases in different contexts as well as a complete set of biphones. The BCC sound engine results in smoother, more natural speech, without sacrificing the ability to quickly "capture" new voices in the biphone inventories for the system.


Analysing Obama Speeches Since 2004

#artificialintelligence

Texts have been downloaded from this site, I have not seen the content of each of the speeches, but the overwhelming majority of these texts were told by Obama during his speeches. Anything else told by somebody else is negligible compared to the overall result of this analysis. According to Wikipedia The lexical diversity of a given text is defined as the ratio of total number of words to the number of different unique word stems.


Speech-to-Speech Translations Stutter, But Researchers See Mellifluous Future

AITopics Original Links

While computer scientists have yet to build a working "universal translator" such as the one first described in the 1945 science-fiction novella "First Contact" and later employed by the crew of the Starship Enterprise on "Star Trek," the hurdles to creating one are being cleared. That is because the practical need for instant or simultaneous speech-to-speech translation is increasingly important in a number of applications. Take, for example, the hypergrowth of social networking and Skype chats that demand bidirectional, reliable, immediate translations. Similarly, when natural disasters strike, the problem of aid workers struggling to communicate with the stricken who often speak other languages can become overwhelming.


Sterling K. Brown finished his Emmys speech backstage after getting cut off

Mashable

At the 2017 Emmys on Sunday night, Sterling K. Brown had his mic cut mid-speech. The 41-year-old actor was thanking the writers for This Is Us, for which he won Outstanding Lead Actor in a Drama Series, after opening his speech with a tribute to the actors who had won the award previously. SEE ALSO: Lena Waithe takes home historic Emmy win for'Master of None' and her speech will make you cry Brown talked of being a fan "first, last and always" of the likes of Breaking Bad's Bryan Cranston, who won in 2014, and Andre Braugher in 1998 -- the last black actor to win the award -- for his part in Homicide: Life on the Street. Yet, unlike the others who've been played off, Brown got a second chance to finish his speech -- albeit in the press room. "You know what, I wouldn't mind finishing.


Frosted Floodgates

Slate

Second, Phillips tells us this case is about "expression." He cites cases where individuals successfully challenged laws that forced them to convey views they did not hold, such as the Jehovah's Witnesses who objected to having New Hampshire's slogan "Live Free or Die" stamped on their license plates. Yet baking a cake is not pure speech: It is at most intermingled speech and conduct. The Colorado law does not force Masterpiece Cakeshop to stamp a pro-gay slogan on its storefront. It does not force the shop to make wedding cakes at all.