Get the newsletter
Microsoft · AI / ML · Filed Jun 8, 2026 · USPTO published Oct 1, 2026 · Oct 1 release

Microsoft Patents an AI That Pulls One Voice Out of a Noisy Video Call

Every video call has the same problem: echoes, crosstalk, and ambient chatter fighting for the microphone. Microsoft is patenting an AI model that handles all of it in one pass, keeping only the voice of whoever you actually want to hear.

Different scenarios of personalized speech extraction from noisy audio, isolating specific voices from background noise and other speakers. Drawing from patent filing US 2026/0301758 A1.
Different scenarios of personalized speech extraction from noisy audio, isolating specific voices from background noise and other speakers.All 11 drawings ↓
Publication number
US 2026/0301758 A1(US20260301758A1)
Applicant
Microsoft Technology Licensing, LLC
Filed · Published
Jun 8, 2026 · Oct 1, 2026
Inventors
Sefik Emre ESKIMEZ, Takuya YOSHIOKA, Huaming WANG, Alex Chenzhi JU, Min TANG, Tanel PÄRNAMAA
Status when we published
Waiting for an examiner
Document
20 claims
US classification
704/202
Parent application
Continuation of 18/172,017 (filed Feb 21, 2023)(18172017)

How Microsoft's call-cleanup AI decides whose voice to keep

Ever been on a video call where you could hear the other person's audio bouncing back at you, plus someone talking in the background on your end? Both problems are usually handled by separate software systems that don't always work well together.

Microsoft's patent describes a single AI model that tackles both at the same time. You tell the system whose voice you want, and it strips out echoes (your own speakers bleeding back into the microphone) and other people's voices in one step, handing you a clean audio track of just your target speaker.

The key twist is the personalization piece. The model learns what your target speaker sounds like and uses that as a guide, so it isn't just reducing noise generically. It's actively looking for one specific voice and discarding everything else.

From the filing · CLAIM 1
a self-attention alignment block configured to use attention to determine a soft-alignment of first features of the first embeddings and second features of the second embeddings, the self-attention alignment block outputting attention weights associated with the soft-alignment; …

Translation: The AI compares different audio streams to figure out which sounds belong together.

Inside the two-stage LSTM pipeline that handles echo then noise

The system takes three inputs: the audio coming from the far end of a call (what the remote participant's speaker is playing), the audio captured by the near-end microphone (which contains the target speaker, background talkers, and the echo of that far-end audio), and a voice profile representing the target speaker's acoustic characteristics.

Those inputs are each encoded into embeddings (numerical summaries that capture audio features) and fed into a machine learning model with two sequential stages.

  • A self-attention alignment block (a component that finds where the far-end and near-end audio overlap in time) computes "attention weights," essentially a map of which moments in the far-end signal match the echo in the near-end recording.
  • A first group of LSTM blocks (Long Short-Term Memory networks, a type of AI that handles sequences by remembering earlier context) uses that map to remove the echo signal.
  • A second group of LSTM blocks then takes the echo-cleaned audio plus the target speaker's voice profile and suppresses any remaining interfering speakers, outputting only the target voice.

Running echo cancellation first and noise suppression second in a single trained model lets each stage inform the other, rather than running as separate, uncoordinated filters.

From the filing · THE ABSTRACT
The machine learning model trained to analyze the far-end signal and the near-end signal to perform personalized noise suppression (PNS) to remove speech from one or more interfering speakers and acoustic echo cancellation (AEC) to remove echoes.

Translation: The system uses machine learning to strip out background noise and echoes from a call.

What this means for Teams calls in crowded offices

For anyone on a video call in an open office or shared space, this is a direct quality-of-life problem. Today's call software often handles echo and background noise through separate components that can interfere with each other or require the user to do nothing special except hope for the best. A unified model that is also personalized to a specific speaker's voice could mean cleaner audio with fewer artifacts.

For Microsoft, which runs Teams across hundreds of millions of users, even a modest improvement in call audio quality at scale is a meaningful product advantage. a growing pile of Microsoft audio and speech-AI filings suggests this is an area the company is treating as infrastructure, not a niche add-on.

Microsoft's 14th filing we've tracked in Voice & speech AI since May follows earlier work on prepping calls for recognition and blending phone and internet for text-to-speech.

Source: US 2026/0301758 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Microsoft patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 11 sheets

11 drawing sheets from US 2026/0301758 A1 · click any drawing to enlarge

AI model for voice separation., drawing sheet 1 from US 2026/0301758 A1
Sheet 1 AI model for voice separation.
AI model for voice separation., drawing sheet 2 from US 2026/0301758 A1
Sheet 2 AI model for voice separation.
AI model for voice separation., drawing sheet 3 from US 2026/0301758 A1
Sheet 3 AI model for voice separation.
Personalized speech extraction examples., drawing sheet 4 from US 2026/0301758 A1
Sheet 4 Personalized speech extraction examples.
Attention mechanism for audio processing., drawing sheet 5 from US 2026/0301758 A1
Sheet 5 Attention mechanism for audio processing.
Steps for personalized noise suppression., drawing sheet 6 from US 2026/0301758 A1
Sheet 6 Steps for personalized noise suppression.
Communication system with client devices., drawing sheet 7 from US 2026/0301758 A1
Sheet 7 Communication system with client devices.
Detailed steps for voice extraction., drawing sheet 8 from US 2026/0301758 A1
Sheet 8 Detailed steps for voice extraction.
Show the other 3 sheets
Microsoft Patents an AI That Pulls One Voice Out of a Noisy Video Call patent drawing, sheet 9
Sheet 9
Microsoft Patents an AI That Pulls One Voice Out of a Noisy Video Call patent drawing, sheet 10
Sheet 10
Microsoft Patents an AI That Pulls One Voice Out of a Noisy Video Call patent drawing, sheet 11
Sheet 11
Patent filing page

Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.