Meet Sanas Noise Cancellation Plus: Redefining Speech Clarity, Fidelity, Robustness, and Adaptability

Background noise is a fact of life — in cafés, open offices, cars, and customer calls. Yet even the best noise cancellation systems make compromises in leaking noise, degrading speech, and deteriorating audio quality.
With Noise Cancellation Plus, Sanas sets a new benchmark on clear communication everywhere, for everyone. Noise Cancellation Plus combines a new proprietary AI model trained on massive real-world datasets to deliver speech that preserves the fullness of emotion, tone, and identity even in the most chaotic environments.
We’ve built a model so powerful, adaptive, and precise that it truly redefines the standard for noise cancellation. Read on to explore how Noise Cancellation Plus redefines the standard for real-time communication clarity.
What’s New in Noise Cancellation Plus
Noise Cancellation Plus introduces major advances across the board in fidelity, robustness, and adaptability.
- Next-Generation Performance: Powered by a new AI model, Noise Cancellation Plus delivers breakthrough gains in both objective metrics and perceptual quality compared with prior Sanas models and the leading solutions on the market.
- Best-in-Class Robustness: Noise Cancellation Plus is our most resilient model yet, engineered to perform consistently across unpredictable, multi-speaker, and high-noise environments.
- Ultra-Fidelity Audio: Expanding beyond low-fidelity (8 kHz) and high-fidelity (16 kHz) audio, Noise Cancellation Plus now also operates at ultra-fidelity (24 kHz) capturing and preserving the full warmth, texture, and detail of human voices.
- Smart Ringtone Passthrough: All Noise Cancellation Plus models support configurable ringtone passthrough, keeping contact-center agents and professionals alert for incoming calls without sacrificing suppression quality.
- Designated Modes for Every Scenario
- Standard Mode: Removes background noise while intentionally preserving all speakers’ voices, well-suited for group calls or shared microphones.
- Voice Isolation Mode: Isolates and preserves only the foreground speaker, removing both background noise and other voices for maximum clarity.
Ultra-Fidelity Audio
For decades, voice communication has run on a legacy standard: 8 kHz audio, productionized in the 1970s to make phone calls efficient. However, at that fidelity, only a fraction of the voice’s frequency range is captured: enough to understand the words, but not the full warmth behind them. Consonants blur, harmonics vanish, and conversation starts to sound flat.
At Sanas, we believe clarity means more than just hearing the words. It means hearing people’s tone, texture, and intent. Our previous bandwidth extension system reconstructed 16 kHz audio in real time from low-fidelity input, restoring the detail that the original signal never contained.
Now, with Noise Cancellation Plus, we’ve gone a step further, introducing ultra-fidelity 24 kHz audio. The result is voice that feels real, full, and effortless to follow, even in noisy or fast-paced conversations.
Low Fidelity (8 kHz) | High Fidelity (16 kHz) | Ultra Fidelity (24 kHz) |
Smart Ringtone Passthrough
Clarity shouldn’t come at the cost of awareness.
For professionals who need to stay alert — like contact-center agents or remote teams handling live calls — Noise Cancellation Plus introduces Smart Ringtone Passthrough, a configurable feature that passes through ringtones so that you can hear an incoming call come in.
It intelligently detects specific alert tones such as ringtones or call notifications and allows them to pass through while keeping everything else silent. You stay focused and responsive without background chaos breaking your concentration.
Original (Input) | Sanas NC Plus | Sanas NC Plus with Ringtone Passthrough |
Standard and Voice Isolation Mode
Imagine you’re on a video call from the middle of a busy office floor with keyboards clicking, teammates chatting, and phones ringing. At first, you’re the only person from your side on the call, so you need every background voice blocked out except your own.
A few minutes later, you wave a colleague over to add their perspective. They step in behind you, and suddenly you want both of your voices included, but not the coworkers talking just a few feet away.
This is exactly the kind of situation Noise Cancellation Plus is built to handle.
Voices don’t just differ in loudness, they carry cues about speaker distance and context. Noise Cancellation Plus reads these cues automatically, distinguishing primary and secondary speakers based on acoustic distance rather than arbitrary volume thresholds. The result: the system knows when to keep additional voices and when to suppress them.
This distinction powers Noise Cancellation Plus’s two operating modes:
- Standard Mode: Keeps all voices within close and medium range, enabling a natural multi-speaker experience while removing environmental noise and background babble.
- Voice Isolation Mode: Retains only the nearest voice, suppressing other voices and distracting noise for maximum primary speaker clarity.

Original (Input) | NC Plus Standard Mode | NC Plus Voice Isolation Mode |
Noise Cancellation Plus’s design recognizes the primary speaker and decides when to include nearby voices or suppress them. The result is a model that adapts naturally to real-world conversations: in a conference call, it preserves colleagues’ voices; on a private call, it keeps only yours.
Noise Cancellation Plus Results and Audio Samples
We compared Noise Cancellation Plus against a competitor using internally developed test sets made up entirely of real-life recordings. At Sanas, we believe that synthesized samples or low-noise public datasets cannot accurately represent real-world conditions. That’s why every sample in our evaluation reflects authentic, everyday environment along with a range of edge cases and unpredictable outliers designed to test robustness.
The results speak for themselves. In both standard and voice isolation modes, Noise Cancellation Plus consistently outperforms in both background noise suppression and voice isolation, delivering cleaner, more natural speech across a wide range of acoustic conditions. Readers interested in the full list of objective quality metrics (NISQA, DNSMOS, and more) can find detailed definitions and references in our upcoming technical deep dive article.
Standard Mode – Background Noise Suppression
When background noise is the main challenge, Noise Cancellation Plus’s Standard Mode removes distracting sounds while preserving nearby voices for natural group conversation.


Original (Input) | Generic Noise Cancellation | Sanas NC Plus Standard Mode |
Rain noise and speech | Heavy noise leakage, syllable suppression (”s” in “so”), and muffled speech at times | Clean voice, noise removed entirely |

Original (Input) | Generic Noise Cancellation | Sanas NC Plus Standard Mode |
Background chatter and noise, multiple people in very close proximity to the microphone | Heavy speech deletion and noise leakage | Speakers in close and medium range from the microphone are kept, primary speaker voice is well extracted |

Original (Input) | Generic Noise Cancellation | Sanas NC Plus Standard Mode |
Loud music and speech | Heavy music leakage in silence and during speech | Music fully removed and disentangled from speech |
Voice Isolation Mode – Background Speech Cancellation
When competing human speech is the main interference, Noise Cancellation Plus’s Voice Isolation Mode focuses solely on the primary speaker, removing background talk without artifacts.


Original (Input) | Generic Noise Cancellation | Sanas NC Plus Voice Isolation Mode |
Siren and background voice | Background voice and noise leakage before and during speech, static noise | No background voice, clear primary speaker voice |

Original (Input) | Generic Noise Cancellation | Sanas NC Plus Voice Isolation Mode |
Speaker in traffic with background voices | Voice leakage during and before speech | No background voice leakage |

Original (Input) | Generic Noise Cancellation | Sanas NC Plus Voice Isolation Mode |
Deteriorated signal with background voice and noise | Background voice leakage and noise leakage | Clean speech, no background voices |
Across both modes, Noise Cancellation Plus consistently achieves higher objective scores and superior perceptual quality in listening tests, validating what users hear in practice. These improvements come without added distortion or latency, demonstrating that high fidelity and real-time performance can truly coexist.
Ultimately, Noise Cancellation Plus goes beyond suppressing noise. It distinguishes and preserves the nuances of human speech to deliver the clarity, warmth, and realism that make every voice sound natural, no matter the environment.
Interested in learning more about the science behind these modes — including how we developed, tested, and verified their performance? Stay tuned for our upcoming blog, where we’ll explore the data, methodology, and real-world results that power Noise Cancellation Plus.
Redefining Clarity in Human Communication
With Noise Cancellation Plus, Sanas moves beyond traditional noise suppression to understand how people actually sound in the world around them. By combining advanced acoustics, AI model design, and real-world simulation, our team has built a system that adapts to any environment without sacrificing the voice's warmth or character.
For enterprises, that means clearer customer interactions, stronger agent confidence, and smoother collaboration across every communication channel. For individuals, it means being heard fully and authentically no matter where you are.
At Sanas, our mission has always been to make communication more inclusive, intelligible, and human. By transforming background chaos into clarity, Noise Cancellation Plus brings us closer to a world where every conversation is clear, connected, and understood.











