Even five years ago, we needed to train systems for each regional accent, but nowadays, Siri copes with Scottish accents

Away from our headsets, speech isn’t really as linear as I have made out. In close proximity to someone speaking, I might whisper a comment to another listener, and still go unheard by anyone else. At a dinner party, I might be involved in more than one conversation at a time, because it is easy, in the 3D space of the real-world, to keep track of who has said what, and to control the volume and direction of my speech to target a specific listener.

However, for speech technology to reach the potential of what it, uniquely, can do well, it still has much further to go. This is good news for the industry, as more and more startups are funded to solve real-world problems, not dealt with by the big players.

http://news24.acaps.cat/gms/Video-brest-v-nice-v-fr-fr-1kmz-3.php

http://vert.actiup.com/vyw/video-cornella-v-atletico-madrid-v-es-es-1hrg-23.php

http://live247.gruposio.es/udo/videos-cornella-v-atletico-madrid-v-es-es-1ihq-1.php

http://svt.munich.es/zzr/Video-metz-v-bordeaux-v-fr-fr-1nzz-23.php

http://live247.gruposio.es/udo/v-ideos-cornella-v-atletico-madrid-v-es-es-1gkm-7.php

https://assifonte.org/media/sja/videos-AEL-Limassol-AEK-Larnaca-v-en-gb-1dys-18.php

http://vert.actiup.com/vyw/Video-cornella-v-atletico-madrid-v-es-es-1hoo-24.php

http://svt.munich.es/zzr/v-ideos-metz-v-bordeaux-v-fr-fr-1una-16.php

http://news24.acaps.cat/gms/Video-brest-v-nice-v-fr-fr-1kzg-20.php

http://live247.gruposio.es/udo/Video-Asteras-Tripolis-Olympiacos-v-en-gb-1wpj30122020-.php

http://vert.actiup.com/vyw/video-Asteras-Tripolis-Olympiacos-v-en-gb-1rsc30122020-.php

http://live247.gruposio.es/udo/Video-Asteras-Tripolis-Olympiacos-v-en-gb-1vyr-15.php

http://vert.actiup.com/vyw/Video-Asteras-Tripolis-Olympiacos-v-en-gb-1uks30122020-15.php

http://news24.acaps.cat/gms/videos-brest-v-nice-v-fr-fr-1lig-27.php

http://svt.munich.es/zzr/video-metz-v-bordeaux-v-fr-fr-1zmj-5.php

http://svt.munich.es/zzr/Video-AEL-Limassol-AEK-Larnaca-v-en-gb-1nov-.php

http://news24.acaps.cat/gms/v-ideos-Brest-OGC-Nice-v-en-gb-1mxn-.php

https://assifonte.org/media/sja/v-ideos-lorient-v-monaco-v-fr-fr-1wmu-20.php

http://svt.munich.es/zzr/videos-AEL-Limassol-AEK-Larnaca-v-en-gb-1dvm-22.php

http://vert.actiup.com/vyw/video-Asteras-Tripolis-Olympiacos-v-en-gb-1dtr-17.php

, and for miles all I could see were trees and trees. There were no sounds other than the crackling of leaves under my shoes when I would pace my space back and forth. Every once in a while, I would test the silence and let out a scream, wanting to see how long it would echo.

Technology to separate speech from different speakers is coming on in leaps and bounds. This is achieved both by analysing the speech more deeply, and by combining the audio data with other sources, like using multiple microphones to measure relative volume and direction, or by using input from cameras to add lip movements and facial expressions to the mix.

More often than not, you’ll be working with stakeholders who aren’t as tech-savvy and may not understand the projects that you are working on. Therefore, it’s your job to communicate and educate your co-workers and stakeholders in a manner that is digestible for them.

Lastly, you may find yourself having to negotiate between time and perfect — in some cases, you’ll want to an extra week or two to improve the accuracy of your model, while your business stakeholders may not see the value in the incremental improvement.

Finally, early identification of certain serious long-term neurological conditions is possible by monitoring subtle changes to speech. This can be done without hospital visits or even without targeting those who are at risk. Conveniently for all concerned, we all speak into our phones and computers all the time, so it would only be necessary to opt in, and give permission for your voice to be analysed, without compromising confidentiality by being recorded or listened to.

A lot of your time will most likely be spent on understanding the data, where it’s coming from and how it’s being manipulated), as well as preparing the data (EDA, data wrangling, feature engineering, etc.). And if you don’t have the data that you need to develop a good model, you’ll have to develop the pipelines to be able to get the data that you need.

Technology has to get as good at listening, and at speaking, as human beings are, and then — in some contexts — get better than we are. Here are a few examples from projects, which I and others have been working on lately.

Nowadays, the latest developments are routinely shared, and the whole industry takes the latest ideas from Google, NVIDIA, Microsoft and a global community of university researchers, and with their blessing, extends them and applies them in new contexts, adding expertise from their own niche professions.

I have spent a lot of time working on systems which analyse accents, mispronunciations and speech impediments. Some people are difficult to understand because they have an unfamiliar accent, or are only just learning a language. We can make it easier to master pronunciation by giving them real-time feedback, but maybe we needn’t bother: morphing accents, and correcting errors in real time are both becoming a reality.

In 2016, Google came up with a new approach to speech synthesis, using WaveNet, a neural network, which can be trained to generate almost any kind of sound, and then training it with real human speech. Once trained, it can be fed with quite robotic synthesized speech, and then make it sound human.

Speech does not only vary by accent, but also by emotional and physical state. When a condition makes someone unintelligible, it is feasible not only to improve intelligibility but to identify what is wrong, perhaps categorising emergency calls, where the speaker is affected by stroke, sedation, drunkenness, concussion, or merely identify that the caller is a child, or speaks a particular language.

Finally, early identification of certain serious long-term neurological conditions is possible by monitoring subtle changes to speech. This can be done without hospital visits or even without targeting those who are at risk. Conveniently for all concerned, we all speak into our phones and computers all the time, so it would only be necessary to opt in, and give permission for your voice to be analysed, without compromising confidentiality by being recorded or listened to.

Computers have made multi-taskers of us all, and sometimes I think that, as an interface, even for interpersonal communications, speech can sometimes set us back: I can be in several text chats at once, but I can’t be on two voice calls. Text and screen interactions have some real advantages, with which speech shouldn’t even try to compete.