TMCnews Featured Article
Speech Recognition and Text to Speech Leader Loquendo Boasts Human-Like Voice Solutions
By Tammy Wolf, TMCnet Web Editor
On the heels of its 10th anniversary, speech recognition and text to speech expert Loquendo (News - Alert) has been empowering its customers to interact with services, technologies and devices with no limitations and in the most natural way possible – by using their voice.
In the last month, the company has been quite busy releasing several innovative voice technologies solutions that will serve market leaders from every business sector around the world. From its newly released MRCP server to new capabilities for its ASR, a solution targeted at grammar-based speech recognition applications, Loquendo continues to make its mark as a best-of-breed provider in the space.
TMC had the opportunity to sit down with Rosanna Duce, vice president of International Sales for Loquendo, at this week’s SpeechTEK (News - Alert) 2011 in New York City, to discuss several of the company’s new developments, as well as what feats it hopes to tackle next.
With 32 languages already integrated into its speech recognition and text to speech solutions, ranging from English, Spanish and European dialects to the more obscure like Arabic, Galician and Mandarin Chinese, Duce said it will be one more year until Japanese is added to the mix.
A rapid, highly accurate speech recognition software solution, Loquendo ASR powers interactive services managing millions of calls every day to achieve automation, effectively search information and create a seamless flow of interactions, and thus save on both time and costs. From automated call centers and multimodal mobile solutions to phone banking and medical dictation, Loquendo’s applications are built to simplify any environment.
Loquendo’s TTS (Text to Speech), which is now powering more than six million user-generated flashcard sets from U.S.-based flashcards and study games site Quizlet.com, functions as a speech synthesis software that reads any text naturally and expressively. From laughing to crying, Loquendo’s synthetic voices are expressive and natural-sounding, even maintaining their native accent.
This extreme likeness to the everyday human being is something Loquendo is committed to achieving in the near future, said Duce.
“In the speech recognition industry, we need to be able to recognize feelings like happiness, anger, as well as gender… to be as close to the human being as possible,” Duce told TMC (News - Alert). “And we’re close to that goal.”
In fact, just last month, Loquendo garnered for the third consecutive year the top prize in the Market Leaders category at the 2011 Speech Industry Awards, receiving high marks in customization options, accuracy and customer satisfaction.
So what’s next for Loquendo?
“We’re trying to develop a product that can be accessed in any environment, using the same core technologies, so people can use the product wherever they are,” Duce told TMC, adding that moving to the cloud is certainly in the near future for the company.
Want to learn more about the latest in communications and technology? Then be sure to attend ITEXPO West 2011, taking place Sept. 13-15, 2011, in Austin, Texas. ITEXPO (News - Alert) offers an educational program to help corporate decision makers select the right IP-based voice, video, fax and unified communications solutions to improve their operations. It's also where service providers learn how to profitably roll out the services their subscribers are clamoring for – and where resellers can learn about new growth opportunities. To register, click here.
Tammy Wolf is a TMCnet web editor. She covers a wide range of topics, including IP communications and information technology. To read more of her articles, please visit her columnist page.
Edited by Chris DiMarco