Speech


How to use Watson Speech to Text utilities to increase accuracy - Artificial Intelligence

@machinelearnbot

I thought I would take a moment to play with Watson Speech to Text and a utility that was released a few months ago. So the purpose of asking about a puppy is that I have a sample conversation system that is about buying a dog. Learn how to use Watson Speech to Text API to increase your accuracy. We've included links S2T utilities download links and sample .wav I thought I would take a moment to play with Watson Speech to Text and a utility that was released a few months ago.


Flipboard on Flipboard

#artificialintelligence

Dictate, a new project from Microsoft's experimental R&D group, Microsoft Garage, is launching today to offer a way to type using your voice in Office programs including Outlook, Word and PowerPoint. Available as an add-in for Microsoft's software, Dictate is powered by the same speech recognition technology that Cortana uses in order to convert your speech to text. An introductory video posted this morning to YouTube offers a preview of how the software works in Word, PowerPoint, and Outlook. It also at launch supports more than 20 languages for dictation, and can translate in real-time into 60 languages.


Open Source Toolkits for Speech Recognition

@machinelearnbot

Typically, this consists of n-gram language models combined with Hidden Markov models (HMM). This article reviews the main options for free speech recognition toolkits that use traditional HMM and n-gram language models. However, Kaldi does cover both the phonetic and deep learning approaches to speech recognition. We didn't dig as deeply into the other three packages, but they all come with at least simple models or appear to be compatible with the format provided on the VoxForge site, a fairly active crowdsourced repository of speech recognition data and trained models.


How to use Watson Speech to Text utilities to increase accuracy - Watson

#artificialintelligence

June 23, 2017 Written by: Simon O'Doherty Key Points: – Learn how to use Watson Speech to Text utilities to increase your accuracy – We've included links so you can download S2T utilities – Sample .wav I thought I would take a moment to play with Watson Speech to Text and a utility that was released a few months ago. The Speech to Text Utils allows you to train S2T using your existing conversational system. So the purpose of asking about a puppy is that I have a sample conversation system that is about buying a dog. From a demonstration from development, it was able to increase a S2T model accuracy from around 50% to over 80%.


Talking to your car is better than ever, thanks to Nuance's voice assistant

Mashable

Nuance Communications is the company responsible for the original voice recognition and speech technology for Siri, and the parent of one of the oldest and most-respected voice recognition systems, Dragon Naturally Speaking. One of the key themes, said Nuance Dragon Drive Solutions Marketing Manager Robert Policano, who was seated behind the driver in the Chrysler, is artificial intelligence and "how we use it on top of speech recognition and natural language processing to make it more contextual, offer more relevant results, and make it more humanized." When Ben-Gigi accepted, Dragon Drive pulled up gas stations with a focus on the brand he preferred. "While Apple is building an Apple experience, Nuance is helping BMW build the BMW experience," said Policano.


Google Now Employs AI to Help You Land a New Job

#artificialintelligence

As promised during its annual developer conference earlier this month, Google launched its search engine for jobs yesterday. Powered by artificial intelligence (AI), this specialized job search uses Google's Cloud Jobs API that launched back in 2016 as part of the company's "AI-first" approach. Instead of requiring users to download a new app, this new AI-powered tool allows job seekers in the U.S. to use Google's existing search function, which are accessible via desktop and mobile. However, Google won't handle any of the actual application process, and will simply direct you to the existing job application site.


Ditch your keyboard in 20 languages with Microsoft's new dictation app

Mashable

A new app add-on from Microsoft Garage, the company's arm for experimental projects, will bring the next-level speech recognition system used by Cortana to transcribe your words in Outlook, Word, and PowerPoint. Dictate can transcribe in 20 languages, and Microsoft claims the AI can provide real-time translation in 60 languages. Voice-based productivity isn't exactly new; Google introduced a dictation feature to Docs last year, even giving users some next-level voice controls to allow for extra formatting and editing power. Microsoft also announced that its speech recognition software was as accurate as humans earlier this year -- but that system hasn't been introduced to its programs just yet.


All in on AI: Artificial Intelligence in the Public Sector

#artificialintelligence

From computer vision systems for autonomous driving to FDA-approved medical imaging, artificial intelligence (AI) is driving public sector innovation. Governments, defense agencies, and other public sector organizations are adding AI into their platform, solutions, and products to perform tasks that usually require human-level intelligence, such as visual perception, speech recognition, decision making, or translation. With the announcement of Amazon Polly, we're excited about the ability to provide an even better experience to these customers by delivering incredibly lifelike voices that will captivate and engage our audience," said John Worsfold, Solutions Implementation Manager, Royal National Institute of Blind People. Health: Ohio Health, a nonprofit health organization, is utilizing evolving speech recognition and natural language processing technology to enhance the lives of its customers.


When AI Can Transcribe Everything

The Atlantic

Despite the recent emergence of browser-based transcription aids, transcription's an area of drudgery in the modern Western economy where machines can't quite squeeze human beings out of the equation. That is until last year, when Microsoft built one that could. Automatic speech recognition, or ASR, is an area that has gripped the firm's chief speech scientist, Xuedong Huang, since he entered a doctoral program at Scotland's Edinburgh University. Huang and his colleagues used their software to transcribe the NIST 2000 CTS test set, a bundle of recorded conversations that's served as the benchmark for speech recognition work for more than 20 years.


Bixby Voice Assistant Release Date: Galaxy S8 Owners Can Now Sign Up, Here's How

International Business Times

Owners of a Samsung Galaxy 8 or Galaxy S8 can now try the smartphones' much-awaited virtual assistant, Bixby -- if you sign up. Bixby has not been officially launched in the United States, but Samsung announced Galaxy 8 owners can now sign up on its site to try a preview version of the feature. If you want to try the Bixby Early Access Program you should hurry, since participation is limited. If you don't have an email account with Samsung, you can go on your device to: Settings Accounts Accounts Add Account Create Account.