Speech recognition from brain activity

June 16, 2015
Speech recognition from brain activity
Brain activity recorded by electrocorticography (blue circles). From the activity patterns (blue/yellow), spoken words can be recognized. Credit: CSL/KIT

Speech is produced in the human cerebral cortex. Brain waves associated with speech processes can be directly recorded with electrodes located on the surface of the cortex. It has now been shown for the first time that is possible to reconstruct basic units, words, and complete sentences of continuous speech from these brain waves and to generate the corresponding text. Researchers at KIT and Wadsworth Center, USA present their "Brain-to-Text" system in the scientific journal Frontiers in Neuroscience.

"It has long been speculated whether humans may communicate with machines via activity alone," says Tanja Schultz, who conducted the present study with her team at the Cognitive Systems Lab of KIT. "As a major step in this direction, our recent results indicate that both single units in terms of as well as continuously spoken sentences can be recognized from brain activity."

These results were obtained by an interdisciplinary collaboration of researchers of informatics, neuroscience, and medicine. In Karlsruhe, the methods for signal processing and have been developed and applied. "In addition to the decoding of from brain activity, our models allow for a detailed analysis of the brain areas involved in speech processes and their interaction," outline Christian Herff und Dominic Heger, who developed the Brain-to-Text system within their doctoral studies.

The present work is the first that decodes continuously spoken speech and transforms it into a textual representation. For this purpose, cortical information is combined with linguistic knowledge and machine learning algorithms to extract the most likely word sequence. Currently, Brain-to-Text is based on audible speech. However, the results are an important first step for recognizing speech from thought alone.

The video will load shortly

The was recorded in the USA from 7 epileptic patients, who participated voluntarily in the study during their clinical treatments. An electrode array was placed on the surface of the cerebral cortex (electrocorticography (ECoG)) for their neurological treatment. While patients read aloud sample texts, the ECoG signals were recorded with high resolution in time and space. Later on, the researchers in Karlsruhe analyzed the data to develop Brain-to-Text. In addition to basic science and a better understanding of the highly complex speech processes in the brain, Brain-to-Text might be a building block to develop a means of speech communication for locked-in patients in the future.

Explore further: Study: Speech processing requires both sides of our brain

More information: "Brain-to-text: decoding spoken phrases from phone representations in the brain." Front. Neurosci. 9:217. DOI: 10.3389/fnins.2015.00217

Related Stories

Study: Speech processing requires both sides of our brain

January 15, 2014

We use both sides of our brain for speech, a finding by researchers at New York University and NYU Langone Medical Center that alters previous conceptions about neurological activity. The results, which appear in the journal ...

Finding thoughts in speech

June 23, 2014

For the first time, neuroscientists were able to find out how different thoughts are reflected in neuronal activity during natural conversations. Johanna Derix, Olga Iljina and the interdisciplinary team of Dr. Tonio Ball ...

Recommended for you

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.