Machine Control with Better Speech Recognition

 Industrial manufacturing view .... 

Intuitive machine control using speech recognition

Research News / February 15, 2023

Fraunhofer researchers at the Fraunhofer Institute for Digital Media Technology IDMT in Oldenburg have developed a speech recognition solution for use in industrial manufacturing. The system works reliably even in noisy environments and can be flexibly adapted to the user’s needs. Employees use intuitive voice commands on the factory floor, allowing them to keep both hands free and work much more efficiently. The Hannover Messe Preview on February 15, 2023, will provide a first look at the research project, including a hands-on demonstration.

Machines such as this milling machining center can be controlled using speech recognition systems and audio technology from Fraunhofer IDMT in Oldenburg. This reliable system can be quickly and easily adapted to customers’ needs.

Experts can experience intuitive machine control live at the Fraunhofer booth during the Hannover Messe 2023.

The practice of using voice-controlled machines in manufacturing was previously considered prone to errors, and as a result, it was hardly ever adopted. Now, Fraunhofer IDMT in Oldenburg has developed a solution that allows machines to be reliably controlled using voice commands. Even on a noisy factory floor, the speech recognition system functions reliably. Employees speak into a wireless headset or a stationary microphone — and in the future, they could use smart hearable technology, which the institute branch for Hearing, Speech and Audio Technology HSA is also working to develop. Loud ambient noise is almost entirely tuned out using a combination of directional microphones and an effective noise-canceling system.

Less walking — and free hands

Marvin Norda, the project manager for Voice Controlled Production at Fraunhofer IDMT, says: “For the first time, our technology is enabling people to control machines in manufacturing using voice commands in a reliable, intuitive way. For manufacturing companies, this means increased efficiency and lower costs.” The technology also has advantages for employees, as contactless machine operation is safe and hygienic for people. When employees are controlling multiple machines, it reduces how far they need to walk — they can use a mobile device to issue voice commands to the equipment from a distance. They have both hands free, allowing them to place a workpiece in position in the work area while giving the robot an instruction such as “lower the arm” or “grip the workpiece” at the same time.

Controlling a machine through voice commands is more efficient than using a control panel or touch panel — clicking through nested menu structures is a cumbersome and error-prone process, whereas direct voice commands involve simple instructions.

“The speech recognition technology can handle hundreds of individual commands depending on the application and is not limited to a particular voice. New or modified commands can be quickly added and trained into the system,” adds Mr. Norda.  ... ' 

Google Makes more Speech Services Available

Impressive array of cognitive speech services, in 120 languages!   Now broadly available with demonstrations at the link.

Cloud Speech-to-Text

Speech-to-text conversion powered by machine learning and available for short-form or long-form audio.

Powerful speech recognition

Google Cloud Speech-to-Text enables developers to convert audio to text by applying powerful neural network models in an easy-to-use API. The API recognizes 120 languages and variants to support your global user base. You can enable voice command-and-control, transcribe audio from call centers, and more. It can process real-time streaming or prerecorded audio, using Google’s machine learning technology.

Some of the Betas in particular are indicative of future direction of capabilities:

Cloud Speech-to-Text features
Speech-to-text conversion powered by machine learning.
Automatic Speech Recognition
Automatic Speech Recognition (ASR) powered by deep learning neural networking to power your applications like voice search or speech transcription.
Global Vocabulary
Recognizes 120 languages and variants with an extensive vocabulary.
Phrase Hints
Speech recognition can be customized to a specific context by providing a set of words and phrases that are likely to be spoken. This is especially useful for adding custom words and names to the vocabulary and in voice-control use cases.
Real-time Streaming or Prerecorded Audio Support
Audio input can be streamed from an application’s microphone or sent from a prerecorded audio file (inline or through Google Cloud Storage). Multiple audio encodings are supported, including FLAC, AMR, PCMU, and Linear-16.
Auto-Detect Language BETA
When you need to support multilingual scenarios, you can now specify two to four language codes and Cloud Speech-to-Text will identify the correct language spoken and provide the transcript.
Noise Robustness
Handles noisy audio from many environments without requiring additional noise cancellation.
Inappropriate Content Filtering
Filter inappropriate content in text results for some languages.
Automatic Punctuation BETA
Accurately punctuates transcriptions (e.g., commas, question marks, and periods) with machine learning.
Model Selection BETA
Choose from a selection of four pre-built models: default, voice commands and search, phone calls, and video transcription.
Speaker Diarization BETA
Know who said what - you can now get automatic predictions about which of the speakers in a conversation spoke each utterance.
Multichannel Recognition BETA
In multiparticipant recordings where each participant is recorded in a separate channel (e.g., phone call with two channels or video conference with four channels), Cloud Speech-to-Text will recognize each channel separately and then annotate the transcripts so that they follow the same order as in real life.  .... " 

Machine Learning Tackles Simultaneous Speech and Object Recognition

Could lead to at least greater efficiency for assistants.  Note the data involved. 

Machine-Learning System Tackles Speech and Object Recognition, All at Once     MIT News  by Rob Matheson

Researchers at the Massachusetts Institute of Technology (MIT) have developed a system that can learn to identify objects within an image, based on a spoken description of the image. When provided with an image and an audio caption, the system can highlight in real-time the relevant regions of the image being described. The system learns words directly from recorded speech clips and objects in raw images, and associates them with one another. The researchers trained the model on a total of 400,000 image-caption pairs, and held out 1,000 random pairs for testing. Said researcher David Harwath, “We wanted to do speech recognition in a way that’s more natural, leveraging additional signals and information that humans have the benefit of using, but that machine learning algorithms don’t typically have access to. We got the idea of training a model in a manner similar to walking a child through the world and narrating what you’re seeing.” ... ' 

Microsoft Claims new Level of Speech Reco Accuracy

Claims to yet better cognitive performance.  Note the claim to improved contextual dialogs, utimately essential to speech interaction.  More open AI please.

Microsoft Claims New Speech Recognition Record, Achieving a Superhuman 5.1% Error Rate
By GeekWire 

Microsoft's Artificial Intelligence and Research Group on Sunday said it achieved a 5.1% error rate for its speech-recognition technology, an improvement over its 2016 record of 5.9% and IBM's 2017 milestone of 5.5%.

Microsoft's Xuedong Huang credits the achievement to "a series of improvements to our neural net-based acoustic and language models."

Huang says the team introduced an additional convolutional neural network integrated with a bidirectional long-short-term memory model for better acoustic modeling.

He also notes the researchers' approach to blend predictions from multiple acoustic models currently does so at both the frame/senone and word levels.

In addition, Huang says the team fortified the recognizer's language model by employing the complete history of a dialog session to predict what is likely to come next, which enables the model to adjust to the topic and local context of a conversation.  ... "