Goto

Collaborating Authors

 noise cancellation


Shokz OpenFit Pro review: Reducing distractions while keeping your ears open

Engadget

Apple could unveil Gemini-powered Siri in Feb. These open-fit earbuds actually make a difference with background noise. Rarely does a set of open-fit earbuds actually impress me. I tend to find them underwhelming because overall sound quality is subpar compared to the more "traditional" in-ear models. The first time I used the Shokz OpenFit Pro ($249.95)


These 360 Bose noise-canceling headphones are just 199 for a limited time during Black Friday

Popular Science

We may earn revenue from the products available on this page and participate in affiliate programs. Bose ANC headphones and earbuds are one of the things I never travel without because they bring the kind of quiet that turns an airplane cabin into a reflection room or an office into an iso booth. Whether you're on a red-eye or running a remote-work coffee-shop marathon, Bose QuietComfort offers just that: mute-the-world magic in an all-day-wear build. And right now, you can take 45 percent off the Bose QuietComfort Headphones for Black Friday. With Quiet and Aware modes plus customizable listening profiles, you can go from "cone of silence" to "hear the boarding call" with a tap.


BanglaTalk: Towards Real-Time Speech Assistance for Bengali Regional Dialects

Hasan, Jakir, Dipta, Shubhashis Roy

arXiv.org Artificial Intelligence

Real-time speech assistants are becoming increasingly popular for ensuring improved accessibility to information. Bengali, being a low-resource language with a high regional dialectal diversity, has seen limited progress in developing such systems. Existing systems are not optimized for real-time use and focus only on standard Bengali. In this work, we present BanglaTalk, the first real-time speech assistance system for Bengali regional dialects. BanglaTalk follows the client-server architecture and uses the Real-time Transport Protocol (RTP) to ensure low-latency communication. To address dialectal variation, we introduce a dialect-aware ASR system, BRDialect, developed by fine-tuning the IndicWav2Vec model in ten Bengali regional dialects. It outperforms the baseline ASR models by 12.41-33.98% on the RegSpeech12 dataset. Furthermore, BanglaTalk can operate at a low bandwidth of 24 kbps while maintaining an average end-to-end delay of 4.9 seconds. Low bandwidth usage and minimal end-to-end delay make the system both cost-effective and interactive for real-time use cases, enabling inclusive and accessible speech technology for the diverse community of Bengali speakers. Code is available in https://github.com/Jak57/BanglaTalk


Google Workspace Promo Code: Up to 14% Off in October 2025

WIRED

Boost your productivity and save with exclusive Google Workspace coupons from WIRED. Get up to 14% off plans for three months, including Starter, Standard, and Plus tiers. Google Workspace is the modern business world's de facto productivity suite, and it's only gotten better over the years. There's the centralization of Google Docs, Drive, and Gmail, of course, but Google has bolstered its productivity suite with an AI infusion via Gemini, as well as simplified its offerings to work for massive corporations all the way down to individual users . If you want to get the best price, you need a Google Workspace promo code.


Advances in Intelligent Hearing Aids: Deep Learning Approaches to Selective Noise Cancellation

Khan, Haris, Asif, Shumaila, Nasir, Hassan, Bhatti, Kamran Aziz, Sheikh, Shahzad Amin

arXiv.org Artificial Intelligence

The integration of artificial intelligence into hearing assistance marks a paradigm shift from traditional amplification-based systems to intelligent, context-aware audio processing. This systematic literature review evaluates advances in AI-driven selective noise cancellation (SNC) for hearing aids, highlighting technological evolution, implementation challenges, and future research directions. We synthesize findings across deep learning architectures, hardware deployment strategies, clinical validation studies, and user-centric design. The review traces progress from early machine learning models to state-of-the-art deep networks, including Convolutional Recurrent Networks for real-time inference and Transformer-based architectures for high-accuracy separation. Key findings include significant gains over traditional methods, with recent models achieving up to 18.3 dB SI-SDR improvement on noisy-reverberant benchmarks, alongside sub-10 ms real-time implementations and promising clinical outcomes. Yet, challenges remain in bridging lab-grade models with real-world deployment - particularly around power constraints, environmental variability, and personalization. Identified research gaps include hardware-software co-design, standardized evaluation protocols, and regulatory considerations for AI-enhanced hearing devices. Future work must prioritize lightweight models, continual learning, contextual-based classification and clinical translation to realize transformative hearing solutions for millions globally.


Embedded Acoustic Intelligence for Automotive Systems

Rajagopal, Renjith, Winzell, Peter, Strbac, Sladjana, Lindström, Konstantin, Hörling, Petter, Kohestani, Faisal, Mehrzad, Niloofar

arXiv.org Artificial Intelligence

Transforming sound insights into actionable streams of data, this abstract leverages findings from degree thesis research to enhance automotive system intelligence, enabling us to address road type [1].By extracting and interpreting acoustic signatures from microphones installed within the wheelbase of a car, we focus on classifying road type.Utilizing deep neural networks and feature extraction powered by pre-trained models from the Open AI ecosystem (via Hugging Face [2]), our approach enables Autonomous Driving and Advanced Driver- Assistance Systems (AD/ADAS) to anticipate road surfaces, support adaptive learning for active road noise cancellation, and generate valuable insights for urban planning. The results of this study were specifically captured to support a compelling business case for next-generation automotive systems. This forward-looking approach not only promises to redefine passenger comfort and improve vehicle safety, but also paves the way for intelligent, data-driven urban road management, making the future of mobility both achievable and sustainable.


The best early Prime Day deals to shop on Amazon today before the July sales event

Engadget

Amazon Prime Day 2024 is officially a couple of weeks away now but we're already starting to see early Prime Day deals pop up. This was expected: Amazon may deem July Prime Day a two-day event, but for years, the online retailer has hosted lead-up deals in order to drum up excitement for the main event. Most early Prime Day deals are exactly that -- early discounts that only Prime members can access -- but every once in a while there are some discounts available to all. We've collected the best early Prime Day deals here, along with the rest of the best discounts on our favorite gadgets that anyone can get from Amazon right now. We'll be updating this post regularly, so check back to see the latest discounts.


Jabra updated its Elite earbuds with an LE Audio case, improved ANC and more

Engadget

Jabra's Elite 10 and Elite 8 Active earbuds debuted in August, but the company isn't waiting for an annual update to unveil a second-generation model for both of those sets. Neither of them will look different, except for some new color options, but there are big upgrades to both. The company has taken this opportunity to make changes to noise cancellation, audio features, spatial sound and other areas. First, both the new Elite 10 and Elite 8 Active will come with what Jabra calls "the world's first LE Audio smart case." This will allow you to plug the charging case into any USB-C or 3.5mm jack to wirelessly transmit sound to the earbuds.


Effects of Dataset Sampling Rate for Noise Cancellation through Deep Learning

Colelough, Brandon, Zheng, Andrew

arXiv.org Artificial Intelligence

Background: Active noise cancellation has been a subject of research for decades. Traditional techniques, like the Fast Fourier Transform, have limitations in certain scenarios. This research explores the use of deep neural networks (DNNs) as a superior alternative. Objective: The study aims to determine the effect sampling rate within training data has on lightweight, efficient DNNs that operate within the processing constraints of mobile devices. Methods: We chose the ConvTasNET network for its proven efficiency in speech separation and enhancement. ConvTasNET was trained on datasets such as WHAM!, LibriMix, and the MS-2023 DNS Challenge. The datasets were sampled at rates of 8kHz, 16kHz, and 48kHz to analyze the effect of sampling rate on noise cancellation efficiency and effectiveness. The model was tested on a core-i7 Intel processor from 2023, assessing the network's ability to produce clear audio while filtering out background noise. Results: Models trained at higher sampling rates (48kHz) provided much better evaluation metrics against Total Harmonic Distortion (THD) and Quality Prediction For Generative Neural Speech Codecs (WARP-Q) values, indicating improved audio quality. However, a trade-off was noted with the processing time being longer for higher sampling rates. Conclusions: The Conv-TasNET network, trained on datasets sampled at higher rates like 48kHz, offers a robust solution for mobile devices in achieving noise cancellation through speech separation and enhancement. Future work involves optimizing the model's efficiency further and testing on mobile devices.


Anker chargers are up to 30 percent off, plus the rest of this week's best tech deals

Engadget

This is the last weekly deal roundup we'll do this year, but unlike other end-of-year posts, we won't be looking back wistfully at the 2023 deals that once were -- all that matters are the ones you can get right now. This week, we're seeing a few sale prices that are still live from Black Friday; snag those before they inevitably go back up. A few new discounts have popped up that actually beat lows from November's shopping holiday, including a Prime-only deal on Amazon's Echo Show 8, all-time lows on Anker charging accessories, and discounts on Apple AirTags and Tile Pro trackers. Until next year, these are the best tech deals that you can still get today. As part of a larger Anker charging accessories sale, our top 30-watt fast charger is 30 percent off.