logo
Clicks & growls: Why AI's hearing the call of the wild

Clicks & growls: Why AI's hearing the call of the wild

Mint29-04-2025
Google has used artificial intelligence (AI) to decode and mimic dolphin sounds, advancing our understanding of marine life. But can AI truly outperform human insight in interpreting animal communication?
Also Read |
Return of Indian tech brands: Is it for real this time?
Dolphins are famously socially skilled, intelligent, agile, joyful and playful, thus sharing many emotional similarities with (some) humans. Just as British ethologist Jane Goodall studied the social and family interactions of wild chimpanzees, Denise Herzing has studied dolphin communication in the wild since 1985, making The Wild Dolphin Project (WDP) the longest running underwater dolphin research project in the world. Google, in partnership with Georgia Tech and WDP, used an AI model to analyse vocal patterns much like a language model, identifying structure and predicting sequences.
Also Read |
Why Pakistan's trade ban is more sound than fury
Dolphins use distinct sounds for different social situations: whistles act like names for individual identification, especially between mothers and calves; squawks often occur during conflicts; and click buzzes are used in courtship. DolphinGemma, Google's 400 million parameter model that runs on Pixel6 smartphones, decodes these sounds by combining audio tech with data from WDP acquired by studying wild dolphins in the Bahamas. On National Dolphin Day (14 April), Google showcased advances to its AI model that can now analyse dolphin vocal patterns and generate realistic, dolphin-like sounds.
Also Read |
Return of the dire wolf: Is this a Game of Clones?
AI is being used to detect how parrots, crows, wolves, whales, chimpanzees and octopuses communicate. NatureLM-audio is the first audio-language model built for animal sounds and can generalize to unseen species. Other projects use AI and robotics to decode sperm whale clicks, or listen to elephants to detect possible warning calls and mating signals.
It aids conservation by monitoring endangered species. Decoding communication reveals ecosystem health, alerting us to pollution and climate change. It enhances human-animal interactions and fosters empathy. AI, combined with satellite imagery, camera traps and bioacoustics, is being used in Guacamaya to monitor deforestation and protect the Amazon, a collaboration between Universidad de los Andes, Instituto SINCHI, Instituto Humboldt, Planet Labs and Microsoft AI for Good Lab.
AI can detect animal sound patterns, but without context— is the animal mating, feeding or in danger?—its interpretations are limited. The risk of humans assuming animals 'talk" like humans do, messy field data, and species-specific behaviours can complicate analysis. AI might identify correlations but not true meaning or intent. Human intuition helps. These systems often require custom models and extensive resources, making large-scale, accurate decoding of animal communication a complex effort.
Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

Shubhanshu Shukla's extraordinary gift to PM Modi stirs emotions — netizens say ‘India rises'
Shubhanshu Shukla's extraordinary gift to PM Modi stirs emotions — netizens say ‘India rises'

Time of India

time3 hours ago

  • Time of India

Shubhanshu Shukla's extraordinary gift to PM Modi stirs emotions — netizens say ‘India rises'

Prime Minister (PM) Narendra Modi met Group Captain Shubhanshu Shukla on August 18, a day after the astronaut returned to India following his historic visit to the International Space Station (ISS). PM hosted Shukla at his Lok Kalyan Marg residence in Delhi. Shubhanshu Shukla's gift to the Prime Minister The prime minister welcomed him with a warm hug and walked alongside him with his arm on the astronaut's shoulder. During the meeting, Shukla gifted PM the Axiom-4 mission patch and showed him pictures of the Earth taken from the ISS. For those unaware, he is the first Indian astronaut to travel to the International Space Station. Shukla also presented the PM with the Indian tricolor that had flown aboard the ISS. This tricolor had been visible in the background when he interacted with PM Modi on June 29 during the early days of the Axiom-4 mission. PM Modi posted on X following the meeting, and wrote, 'India is proud of his feat'. Netizens also reacted with pride and admiration, sharing their excitement about India's presence in space and celebrating Shukla's achievements. Had a great interaction with Shubhanshu Shukla. We discussed a wide range of subjects including his experiences in space, progress in science & technology as well as India's ambitious Gaganyaan mission. India is proud of his feat.@gagan_shux One user wrote, 'Truly inspiring! Shubhanshu Shukla's journey reflects the spirit of New India, ambitious, innovative, and ready to conquer space.' Another dedicated a long poem, with verses saying, 'In their meeting, teacher and voyager spoke of dreams that turn to orbits, of courage that carries the sky on its shoulders. India rises.' Truly inspiring! 🚀 Shubanshu Shukla's journey reflects the spirit of New India - ambitious, innovative, and ready to conquer space. 🇮🇳✨ Had a great interaction with Shubhanshu Shukla. We discussed a wide range of subjects including his experiences in space, progress in science & technology as well as India's ambitious Gaganyaan mission. India is proud of his feat.@gagan_shux Shukla's role in Axiom-4 mission Shubhanshu Shukla was a key part of the Axiom-4 private space mission, which launched from Florida on June 25 and reached the International Space Station (ISS) the following day. The mission concluded with his return to Earth on July 15. Over the course of 18 days in orbit, he worked alongside astronauts Peggy Whitson from the United States, Slawosz Uznanski-Wisniewski from Poland, and Tibor Kapu from Hungary. Together, the crew carried out more than 60 scientific experiments and engaged in 20 outreach programmes while stationed at the ISS. Instructions PM Modi gave him before the mission He had also documented his learning, training, and stay on the ISS as directed by PM Modi to support India's future missions, including Gaganyaan. 'I remember very well the homework given to me by the prime minister. And I completed it very well. I am very excited to come back and share it with you all. I am confident that all that knowledge is going to prove extremely useful and crucial for us, for our own Gaganyaan mission,' Shukla said on August 1 during a press meet. To stay updated on the stories that are going viral follow Indiatimes Trending.

Opposition meet to pick V-P candidate remains inconclusive, another round of parleys on August 19
Opposition meet to pick V-P candidate remains inconclusive, another round of parleys on August 19

The Hindu

time4 hours ago

  • The Hindu

Opposition meet to pick V-P candidate remains inconclusive, another round of parleys on August 19

The meeting of INDIA bloc leaders on Monday (August 18, 2025) at Congress president Mallikarjun Kharge's official residence to decide the Opposition candidate for the Vice-President's post remained inconclusive. 'A meeting of leaders of all Opposition parties in Parliament will be held at 12:30 PM tomorrow Tuesday Aug 19th at 10, Rajaji Marg,' Congress communications chief Jairam Ramesh said in a post on X. The Opposition bloc is likely to announce its choice on Tuesday (August 19, 2025). According to sources, the Congress president, who is also the Leader of the Opposition (LoP) in the Rajya Sabha, was committed to fielding a candidate and not conceding without a contest. On Sunday night, Defence Minister Rajnath Singh had reached out to the leaders of some Opposition parties, including Mr. Kharge for unanimously electing the new Vice-President. Sources said the Opposition wants to field a non-political face who has national standing and stature for the second-highest constitutional position in the country. The vice-presidential election, necessitated by the sudden resignation of incumbent Jagdeep Dhankhar last month, is scheduled for September 9. The last date for filing nominations is August 21. Though no name was finalised, several possible candidates were considered. According to sources, on DMK's suggestion, Indian scientist Mylswamy Annadurai, who during his tenure at ISRO worked on two of the major missions of ISRO, namely Chandrayaan-1 and Mangalyaan, was also discussed. The Trinamool Congress, however, was of the opinion that it would be 'reactive' to field another Tamilian in response to the NDA's vice-presidential candidate — Maharashtra Governor C.P. Radhakrishnan. Mr. Annadurai hails from the same Kongu region as Mr. Radhakrishnan. His scientific and apolitical background is an advantage. If a consensus on Mr. Annadurai's candidature emerges within the Opposition ranks and if he agrees to contest, it will help the DMK and its allies politically as they will not be seen as 'anti-Tamil' in opposing Mr Radhakrishnan. Another name that is said to have been discussed is Tushar Gandhi, the great-grandson of Mahatma Gandhi, sources claimed. There were also some reservations among RJD and SP leaders about contesting the vice-presidential polls since the numbers are loaded in favour of the NDA. They argued that since the Opposition does not have the requisite numbers, it should let this election go in view of the upcoming Bihar polls, which they argued needs more attention. The SP also argued that the Opposition should focus its energy on its campaign against the ongoing Special Intensive Revision (SIR) of electoral rolls. 'So far, we have presented a united front, and any cross voting in VP's election would send a wrong message,' a senior SP leader opined. (With inputs from B. Kolappan)

IIIT-A researchers develop AI tech for real time crop disease detection in Indian farms
IIIT-A researchers develop AI tech for real time crop disease detection in Indian farms

Time of India

time5 hours ago

  • Time of India

IIIT-A researchers develop AI tech for real time crop disease detection in Indian farms

Prayagraj: In a groundbreaking advancement for Indian agriculture, researchers at the Indian Institute of Information Technology (IIIT) Allahabad developed an innovative technology that allows farmers to detect crop diseases directly in their fields without needing to consult agricultural experts. This cutting-edge solution uses a combination of Artificial Intelligence (AI), Internet of Things (IoT), Deep Learning, and Federated Learning to analyse plant health based on leaf images and environmental conditions. This AI model— CVGG-16 was developed by Pramod Kumar Singh, a research scholar under associate professor and head of the Information Technology department at IIIT-Allahabad, Manish Kumar. This model was published in the international journal Internet of Things by Elsevier. The CVGG-16 model was trained on real-world images from farms — including dusty, low-light, or weather-affected conditions — making it robust and reliable across various regions and climates. What sets this model apart is its multi-concept data fusion network, which doesn't rely solely on photos. It integrates sensor data such as soil moisture, temperature, humidity, and weather patterns, allowing it to provide highly accurate analysis of a plant's health. by Taboola by Taboola Sponsored Links Sponsored Links Promoted Links Promoted Links You May Like American Investor Warren Buffett Recommends: 5 Books For Turning Your Life Around Blinkist: Warren Buffett's Reading List Undo "For testing the viability of the model, we collected the sample data of the farms around Prayagraj, and we can assure that the model not only saves the precious time of the farmers (when it comes to identifying the health of the crop) but also provides precise information regarding any diseases very much in the preliminary stage, which helps in containing the same in an effective manner," said Manish Kumar. The model achieved an impressive accuracy of 97.25% and in specific tests, it recorded 96.75% accuracy in identifying maize diseases and 93.55% in potato disease detection. A key innovation in this project is the implementation of Federated Learning, which ensures that farmers' data remains private. Instead of sending data to a central server, the model is trained locally near the farms, using a new algorithm named Extreme Client Aggregation. This ensures data privacy and decentralisation while still achieving high performance across datasets from different geographical regions. Since we have the picture of the entire farmland it is easier to spot the 'culprit' even in the deepest part of the crop, he added. Prof Manish Kumar emphasised the model's scalability and adaptability, stating that it can be applied to any crop in any region across India. Whether it's maize fields in North India or potato farms in the South, the model's multi-layered structure allows it to adjust to varied agricultural conditions. The researchers aim to make the technology even more accessible by developing mobile-based solutions and local language interfaces to ensure that small and marginal farmers can benefit from this advancement. This breakthrough could mark a turning point in Indian agriculture, empowering farmers with real-time, intelligent diagnostics — and ensuring healthier crops with minimal dependency on external consultations, he said. Stay updated with the latest local news from your city on Times of India (TOI). Check upcoming bank holidays , public holidays , and current gold rates and silver prices in your area.

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into a world of global content with local flavor? Download Daily8 app today from your preferred app store and start exploring.
app-storeplay-store