Researchers at the University of Moncton, Canada, have developed ECOGEN, a deep learning tool that generates lifelike bird sounds to enhance samples of underrepresented species. By expanding sound libraries for rare birds, it improves the accuracy of bird song identification tools used in ecological monitoring. The researchers found that adding synthetic bird song samples to a bird song identifier improved classification accuracy by 12% on average. ECOGEN can also be applied to other animals like mammals, fish, insects, and amphibians.
Meet ECOGEN: A Novel Deep Learning Approach Designed to Generate Realistic Bird Songs for Biologists and Ecologists
The advent of deep learning has had a significant impact on various fields, including the monitoring of rare birds through their songs.
Differentiating between birds based on their songs has become easier with the availability of mobile applications and software for ecologists and the general public. However, a major problem arises when the identification software encounters an unfamiliar bird species or one with few reference recordings.
To address this problem, researchers at the University of Moncton, Canada, have developed ECOGEN. This innovative solution generates lifelike bird sounds to enhance samples of underrepresented species. These enhanced samples can then be used to train audio identification tools used in ecological monitoring.
Generating audio presents several challenges, including the need for a large number of samples for synthesis. Different formats are used for processing audio files, but many of these formats result in a loss of information, making it difficult to produce high-quality audio samples. The waveform representation, which records sound pressure amplitude in the time domain, is one of the most prevalent formats that preserves information integrity without loss.
ECOGEN addresses these challenges by creating new instances of bird sounds to improve AI models. It expands sound libraries for species with limited wild recordings without harming the animals or requiring additional fieldwork.
The researchers found that adding synthetic bird song samples produced by ECOGEN to a bird song identifier improved bird song classification accuracy by an average of 12%. Dr. Nicolas Lecomte, one of the lead researchers, highlighted the urgent need for automated instruments like acoustic monitoring to track changes in biodiversity caused by global fluctuations in animal populations. However, current AI models used for species identification in acoustic monitoring often lack comprehensive reference libraries.
The researchers emphasized that creating synthetic bird songs can contribute to the conservation of endangered bird species and provide valuable insights into their vocalizations, behaviors, and habitat preferences.
Dr. Lecomte also mentioned that while ECOGEN was developed for birds, it could potentially be applied to other types of animals such as mammals, fish, insects, and amphibians.
ECOGEN operates by transforming bird song recordings into spectrograms, which are visual representations of sounds. It then generates new AI images based on these spectrograms, thereby augmenting the dataset specifically for rare species with limited recordings. These newly generated spectrograms are converted back into audio format to train bird sound identification models. The researchers used a dataset of 23,784 wild bird recordings from around the world, covering 264 different species.
If you want to evolve your company with AI, stay competitive, and use it to your advantage, consider Meet ECOGEN: A Novel Deep Learning Approach Designed to Generate Realistic Bird Songs for Biologists and Ecologists.
Discover how AI can redefine your way of work:
- Identify Automation Opportunities: Locate key customer interaction points that can benefit from AI.
- Define KPIs: Ensure your AI endeavors have measurable impacts on business outcomes.
- Select an AI Solution: Choose tools that align with your needs and provide customization.
- Implement Gradually: Start with a pilot, gather data, and expand AI usage judiciously.
For AI KPI management advice, connect with us at hello@itinai.com. And for continuous insights into leveraging AI, stay tuned on our Telegram or Twitter @itinaicom.
Spotlight on a Practical AI Solution: AI Sales Bot
Consider the AI Sales Bot from itinai.com/aisalesbot. It is designed to automate customer engagement 24/7 and manage interactions across all customer journey stages.
Discover how AI can redefine your sales processes and customer engagement. Explore solutions at itinai.com.
