• There are no suggestions because the search field is empty.
Manuel-Rivera-Morales’-Voice-Re-created-by-AI-for-the-Olympic-Games-Respeecher-voice-cloning-case-study
Manuel-Rivera-Morales’-Voice-Re-created-by-AI-for-the-Olympic-Games-Respeecher-voice-cloning-case-study-1
Listed to the revived voice of sportscaster Manuel Rivera Morales

00:00

Manuel Rivera Morales’ Voice Re-created by AI for the Olympic Games

Manuel Rivera Morales gained nationwide fame in Puerto Rico during the 1960-80s when he covered BSN basketball games live, first on the radio and later on television.

Puerto Ricans have long associated the voice of Rivera Morales with the notable success of their basketball team in the 70s and 80s. Even today, Rivera Morales is considered by many to be the best sportscaster in Puerto Rican history and one of the best in the world.

The DDB agency and Respeecher partnered to revive his memorable voice with the help of artificial intelligence (AI). The project was devoted to the National Women's Basketball Team, which made its debut at the Olympic Games for the first time, playing against China.

The idea was for the sportscaster to broadcast the match, which would be an absolute surprise for the nation. 

The result was an emotional performance in which the voice of Rivera Morales narrated the Puerto Rico match against China on Tuesday, July 27, sharing the broadcast with the commentator Natalia Meléndez.

This project has been recently recognized by the SME Awards 2022 and has won three awards in the following categories:

  1. For Innovative Use of Technology - gold award
  2. Social media - bronze award
  3. Branded content - gold award

SME is an association recognizing the effective integration of social media in marketing campaigns, public relations, advertising, and promotions, as well as creating new digital solutions for businesses. 

The Project in Numbers

This project is one of the first where Respeecher worked with such a large volume of data in such a short time.

1h 50min

Match length between the women's national teams of China and Puerto Rico.

5 Hours

Respeecher spent on transforming source speech into Morales' speech.

10 Days

Training a machine learning model to be able to synthesize Morales' voice.

So how was the voice of the broadcasting legend cloned?

First, let's briefly describe how speech synthesis technology works.

In short, you have the voice of the person you want to clone (also called the target voice). You also have the voice of the person that you intend to transform into the target voice (this is called the source voice).

And there is a medium, controlled by AI, which studies the target's voice, understands its features, and then transforms the source's voice into the target's. The services of such a medium are exactly what Respeecher provides.

Respeecher built an audio version of the super resolution algorithm to deliver the highest resolution audio, even in cases when the client doesn't have high-res sources available. Learn more about it by downloading this whitepaper about Respeecher's audio super-resolution algorithm.

This is not the first time we resurrected a sport legend’s voice - we also created a digital Vince Lombardi for the 2021 Super Bowl LV. It’s just that this time we were working under such difficult conditions.

Please see what Vitalii Knyr, the Head of Delivery at Respeecher pointed out as main challenges in this project:

  1. Fresh/Experimental model
    When we received the target data we put all our hopes in the new experimental model, which theoretically should have worked better with noisy samples, but we didn't have enough experience with applying it to commercial projects.
  2. Language
    Since we didn't have anyone in the team who spoke Spanish, we were not sure if the conversion worked well until we shared the result with DDB. It was a great relief when the client responded "Thank you so much! The sound is perfect!".
  3. Zeitnot
    We usually have a couple of days between receiving the final lines to convert and sharing the result with the client, but in this case, it was a couple of hours to do the job on our end. On top of the fact that we didn’t have anyone that could speak Spanish, we only had one shot to do our work well and we couldn't check if it was good or not until the client returned to us the next day.
4. Data quality
All kidding aside - that was the most complex target data we had ever worked with. The recordings suffered from quality issues of all kinds:
  • background noise from the game and audience
  • low sampling rate (16KHz)
  • outdated and low-fi microphones
  • information/quality lost when transferring data from analog (VHS, old recorders, etc.) to digital format, and many others.

5. Time Zone difference
Since the Respeecher team was about 9,000 kilometers away from the client, we had to adjust our working schedule and work overnight to reduce delays in communication and delivery.

 

Thanks to constant improvements to our AI algorithms, we were able to deal with all the challenges. Not only were we able to clone Morales’ voice using antiquated data, but we synthesized his voice for the entire broadcast in just 5 hours!

It was remarkable, not only for ourselves but for our partners from the DDB as well:

"Discovering Respeecher was the highlight of our project. They agreed to work with the task even when our training data was not of the best quality. The result was fantastic, and the level of detail was just outstanding." 

-Joseph Lopez, Marketing Technology Director of DDB Latina

So, we spent 10 days training the AI system's algorithms and 5 hours on the synthesis itself. If you've ever worked in audio production, you can certainly understand how impressive this timeframe is for a 2-hour audio record.

Project's Results and Cultural Impact 

Against the background of discussions about the negative impact of deepfake technologies, it is difficult to overestimate the positive effect of this project.

While working on the project, we not only cooperated with partners from DDB but also with the family of Rivera Morales. For us, this project has become much more than regular work, mainly due to the warm reaction of his family and the people of Puerto Rico.

Working with Reespecher was a unique experience. Their attentiveness to detail and dedication to this project allowed us to reconnect with one of our lost narration idols in Puerto Rico, Manuel Rivera Morales, on a new level. It gave his family and PR a glimpse of what could have been if he was still alive and narrating all sorts of Olympic sports games. It was truly magical to see this project come alive.

Respeecher-voice-cloning-testimonial-Edgardo-Manuel-Rivera-CEO-DDB-Latina

Edgardo Rivera, President & CEO DDB Puerto Rico

"Dad is alive!" - were the first words of Rivera Morales’ daughter when she heard her father's voice commentating the match.

In comments in the press and on social media, Puerto Ricans also warmly embraced the revival of the commentator's voice from the past. This voice brought people back to a happy time in their youth along with remembering the past successes of the Puerto Rican national team.

This is now one of the hot topics in Puerto Rico and beyond. Respeecher's level of quality and production speed directly states that marketing agencies, filmmakers, and content creators can be more ambitious in their ideas. We have the technology to tackle the toughest challenges.

As for our role in this project, we are always happy to work with history. Resurrecting the voices of historical characters creates a connection between generations separated by time. Past figures can bring a bit of optimism into the present, shake off good memories or make you reflect on some eternal problems.

The potential of our technology for educational and museum projects is genuinely invaluable. We are confident that even more ambitious resurrection projects await us in the future. And that's great because technology should serve the best of our motives.

Reviews

review_avatar

Reid Hoffman

LinkedIn Co-founder, Microsoft Board Member, Investor, Podcaster

review_avatar

Bear Grylls

TV presenter and adventurer

review_avatar

Jennifer Trent

Head of Post Production at Blumhouse

review_avatar

Halsey Burgund

Co-Director In Event of Moon Disaster

review_avatar

Ryan Steelberg

President and co-founder of Veritone

review_avatar

David Romberg

Media, Communication & Film Studies, Muhlenberg College

review_avatar

Abigail Savage

Sound Designer and Supervisor, Actress

review_avatar

Tim Jones

Emmy Award Winning Animation Producer

review_avatar

Michael York

Actor, Producer

review_avatar

Joseph López Osorio

Marketing Technology Director, DDB Latina

review_avatar

Edgardo Rivera

President & CEO, DDB Puerto Rico

review_avatar

Joshua Madoff

Composer, Actor

review_avatar

James Tumminia

Producer & President at Italus Films

review_avatar

Sophie Robinson

Director, 141 Productions

review_avatar

Steve Isaacs

EVP, Legion Creative

review_avatar

Derek Kedell

Producer, Renegade Animation, Inc.

review_avatar

Jacob Mosler

Line Producer, Religion of Sports

review_avatar

Bev Standing

Voice Over Actor & Coach

Respeecher also matched my voice to Scott’s professional reading of the Impromptu text. The end result is a nearly perfect audio artifact with amazing intonation. It sounds flawlessly human—though a bit less of a match to “my” voice than the Vall-E recording—and most importantly, similarly didn’t require multiple days of my time to record. If we hadn’t prioritized releasing an early version to show folks what that sounded like, the Respeecher team was confident that with more iterations we could have gotten it near-perfect.
We worked with Respeecher to recreate my voice in Ukrainian to as part of our education initiative ‘BecomingX Ukraine’. The technology is phenomenal and the result is astounding – I never thought I’d hear myself speaking fluent Ukrainian! Well done and thank to all the team for all your incredible work you are doing. We’re forever grateful and proud to partner with you.
We used Respeecher to de-age the voice of a well-known actor in one of our movies. We were nervous that it wouldn’t work very well since the actor is in her 80s and we needed to de-age her down to mid-forties. Even though there was such a huge age jump, the end result from Respeecher was amazing, and added a level of authenticity to our movie. Everyone from our director through our entire post team was excited to work with Repeecher. Hopefully we will be able to do so many more times in the future.
We worked with Respeecher on a film called ‘In Event of Moon Disaster’ first shown at the Amsterdam Documentary Film Festival 2019. They helped us create a synthetic voice of Richard Nixon to bring to life a never-read contingency speech in case the Apollo 11 mission went badly. We created a highly realistic film, in a large part due to their work. ‘In Event of Moon Disaster’ shows the creative possibility of voice replacement technology as well as highlighting just how realistic deepfake technologies can be, acting as a civic engagement project for the public along with contextual and educational resources.
For Veritone, the most important thing is ensuring our clients get access to technology without compromising on the ability to protect, the delivery speed and quality, and in this case, of the generated content. Respeecher's technology meets both requirements and has a proven track record of working with tier one projects.
When I approached the team at Respeecher with a very sensitive and personal documentary project, I didn't know what to expect. I’m happy to say that it has been an amazing experience. They are extremely professional, ethically minded and are genuinely passionate about bringing their innovative technology to the world. Their approach to the voice cloning process is highly personal and transparent. As a documentarian, it was important to me that the approach was ethical and human focused. The Team at Respeecher delivered on their promises and I could not be happier with the results.
Respeecher is a remarkable tool for Sound Editors. It delivers very high-fidelity recreations of a target voice, with transparent performance-matching of its source. It blows text-to-speech out of the water! The effect is uncanny and incredibly effective and I can imagine a whole slew of uses going forward. I am very excited to have discovered Respeecher, and it will be my go-to for voice recreation in the future, without question.
Respeecher's source/target conversion of Mr. York's speaking voice demonstrably opens doors for the entertainment, education, and healthcare fields. Suffice it to say, it was an absolute honor to collaborate with them. Their brilliant accomplishment and timely delivery have allowed our humble project to be a success, exceeding our expectations for what's even possible.
I am very grateful to Respeecher for giving my words and work a whole new lease on life. The technique involved is as ingenious as it is amazing, and promises a great future for all those involved in voice work. With Respeecher, the quality of the re-worked passages is indistinguishable from the original. History comes almost miraculously alive again. I heartily endorse this product.
Discovering Respeecher was the highlight of our project. They agreed to work with the task even when our training data was not of the best quality. The result was fantastic, and the level of detail was just outstanding.
Working with Reespecher was a unique experience. Their attentiveness to detail and dedication to this project allowed us to reconnect with one of our lost narration idols in Puerto Rico "Manuel Rivera Morales" on a new level. It gave his family and PR a glimpse of what could have been if he was still alive and narrating all sorts of Olympic sports games. It was truly magical to see this project come alive.
Working with Respeecher has been incredible. Their team was meticulous and patient, walking us through the process of developing an accurate model... and the final result was nothing short of miraculous. It really sounds like we’re hearing our (deceased) subject speaking again. Something I never would have thought was possible.
From the introduction to Respeecher’s innovative and state-of-the-art products to the thorough and quick technical support, I immediately felt that I found the perfect partner and technology for my projects’ needs. During our discussions, the team offered other creative options that assured me we were on the same page and had my project’s success as a top priority. The Respeecher team members are consummate professionals.
Making a film which was so sensitive we needed a company who understood the sensibilities and ethical issues we were dealing with. From the first meeting with them, Respeecher acted with respect and professionalism, delivered what we wanted brilliantly, efficiently and to spec.
When Legion Creative took on the challenge of bringing MTV’s Kurt Loder back to his mid ’90s glory for the Showtime original Yellowjackets, we needed a resource to bring his voice in line with his de-aged visual appearance. Respeecher worked quickly, with clear communication and helped us achieve the time-warping magic we were looking for.
Using the Respeecher technology as a powerful filter for our recorded dialogue allowed us to quickly solve a voice-over challenge that could have completely derailed our production timeline and set us back several months. Their easy-to-use online web interface allowed us to resolve our problem in a matter of weeks and with very minimal impact on our overall schedule. Their friendly staff were extremely responsive to our feedback and provided excellent guidance on the use of the amazing technology.
Respeecher brought the voice of WILT CHAMBERLAIN sonically back to life allowing Wilt to posthumously narrate his own documentary series GOLIATH [Showtime & Paramount+]. Our experience working with their team was a pleasure from start to finish. They embraced the creative challenge of building a practically perfect replication of Wilt's voice from hours of archival to carefully match the narration led by our voiceover actor's performance of Wilt's own words selected from his books. Their technicians paid fastidious attention to detail and contineud to work with our directors feedback to adjust the nuance of Wilt's voice until it was seemingly flawless. The Estate of Wilt Chamberlain authorized our team to create a 3-hour series documenting his extraordinary life; so naturally it was a huge relief when we shared the final WILT converted VO narration and received a unanimous approval from his family. Thank you again to Respeecher! Your professionalism, commitment to detail and excellence surpassed our expectations. Your nuanced work brought Wilt's voice back to life will be cherished in GOLIATH eternally.
Working with Respeecher has provided me to control of where my voice is used, the opportunity to provide consent to my voice being used and receveing compensation.
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar
review_avatar

Ready to Replicate Voices?

Want to see our technology in action? Get a demo today.

REQUEST A DEMO