US 11715457

U.S. Patent 11715457, titled "Real time correction of accent in speech audio signals," was issued to Sanas Ai Inc. (current assignee) on August 1, 2023. The inventors are Andrei Golman and Dmitrii Sadykov. The patent was filed on December 19, 2022.

Abstract:
The patent describes systems and methods for real-time correction of accent in speech audio signals. The method involves dividing a speech audio signal into input chunks, extracting acoustic features and accent-reduced linguistic features from these chunks and their associated context, and receiving a speaker embedding for a human speaker. These components (speaker embedding, acoustic features, and linguistic features) are then provided to a synthesis module to generate a melspectrogram with a reduced accent. Finally, a vocoder uses the melspectrogram to generate an output chunk of an output audio signal.

Plain-language overview of independent claims:

• Independent Claim 1: This claim outlines a method for real-time accent correction in speech. It involves taking a speech audio signal and breaking it into small segments called "input chunks." For each chunk, the system extracts two types of information: "acoustic features" (like pitch and energy) and "linguistic features" (which have had the accent reduced). This extraction uses the current chunk and some preceding audio data (context). The system also gets a "speaker embedding," which represents the unique voice characteristics of the speaker. Finally, it uses the speaker embedding, acoustic features, and linguistic features to create a new audio segment (an "output chunk") that has a corrected accent.

Regarding CAFC 2026 dockets for patent 11715457, the provided search results indicate active litigation related to this patent. Specifically, a PTAB case IPR2026-00275 was filed and is pending, and a US case was filed in the California Northern District Court (case 3:25-cv-05666). The petitioner for the IPR case is "Unified Patents PTAB Data."

US Patent 11,715,457 is involved in at least two known litigation cases as of April 26, 2026.

Here are the details for each case:

1. PTAB Case

   • Plaintiff(s)/Petitioner(s): Not explicitly stated, but the source of the data is "Unified Patents PTAB Data".
   • Defendant(s)/Patent Owner: Sanas Ai Inc. (current assignee of the patent)
   • Jurisdiction: Patent Trial and Appeal Board (PTAB)
   • Case Number: IPR2026-00275
   • Filing Date: 2026 (indicated by the case number IPR2026-00275)
   • Outcome/Current Status: Pending

2. US District Court Case

   • Plaintiff(s): Not explicitly stated.
   • Defendant(s): Sanas Ai Inc. (current assignee of the patent)
   • Jurisdiction: California Northern District Court
   • Case Number: 3:25-cv-05666
   • Filing Date: 2025 (indicated by the case number 3:25-cv-05666)
   • Outcome/Current Status: No specific outcome is provided; the case is listed under "litigation".

Proceedings overview

One Inter Partes Review (IPR) proceeding, IPR2026-00275, is on file against US patent 11715457 and is currently in the pre-institution "Pending" phase. This means the Patent Trial and Appeal Board (PTAB) has not yet decided whether to institute a trial. For a defendant, this creates uncertainty, as the validity of the patent's claims is currently being challenged but no claims have been canceled or confirmed patentable by the PTAB.

IPR2026-00275 — Krisp Technologies, Inc. v. Sanas Ai Inc.

• Type: Inter Partes Review
• Filed: 2026-03-18
• Status: Pending. The petition has been filed, and the PTAB is currently reviewing it to determine whether to institute a trial. The last modification to its status was on 2026-05-26.
• Judge panel: Not yet publicly assigned.
• Petition grounds: Details regarding the specific claims challenged, the prior art references cited, and the statutory bases (§ 102 for novelty and/or § 103 for obviousness) are typically made public upon institution of the trial. As of 2026-05-29, the proceeding is in its pre-institution phase.
• Institution decision: Not yet issued. The statutory deadline for the PTAB to issue an institution decision is six months from the filing date, which is 2026-09-18.
• Final Written Decision: Not applicable, as the proceeding is in the pre-institution phase.
• Settlement / termination: Not applicable, as the proceeding is in the pre-institution phase.
• Appeal: Not applicable, as no Final Written Decision has been issued.
• Defensive value: This pending IPR indicates an active challenge to the validity of US11715457. While no claims have been canceled, the existence of a live IPR means the patent's claims are under scrutiny. The outcome of the institution decision (due by 2026-09-18) will be critical for assessing the patent's strength.

Strategic summary

All claims of US11715457 are currently UNTESTED by a PTAB Final Written Decision, as the single IPR filed against it, IPR2026-00275, is still in its pre-institution "Pending" phase. There are no claims that have been formally CANCELED or SUSTAINED by the PTAB at this time. Sanas Ai Inc. is identified as the current assignee of the patent.

Regarding estoppel, the provisions of 35 U.S.C. § 315(e)(2) would apply to the petitioner, Krisp Technologies, Inc., and parties in privity with them, only if a Final Written Decision is issued. If a Final Written Decision were to be issued, Krisp Technologies, Inc. and its privies would be estopped from asserting in a civil action or another USPTO proceeding that a claim is invalid on any ground that Krisp Technologies, Inc. raised or reasonably could have raised during the IPR. Since the IPR is still pending institution, no estoppel has yet attached. Therefore, for a defendant currently facing assertion of this patent, prior-art grounds remain broadly available until an institution decision, and potentially after if institution is denied or only partially granted.

As for pattern signals, only one IPR has been filed against US11715457 to date, IPR2026-00275. The petitioner is Krisp Technologies, Inc., and the case is still in its initial stages. It is too early to discern any aggressive appeal patterns from the patent owner or a history of multiple challenges from the same petitioner or defensive aggregators based on the current single, pending proceeding.

Recommended next steps

• Monitor IPR2026-00275 closely: The most immediate critical milestone is the institution decision, which is due by 2026-09-18. This decision will indicate which claims (if any) the PTAB believes are likely unpatentable and will proceed to trial. The institution decision, when issued, will be available on the USPTO PTAB E2E system.
• Review the petition: Once the institution decision is made public, if the trial is instituted, the petition and the grounds asserted by Krisp Technologies, Inc. should be thoroughly reviewed to understand the scope of the challenge.
• Assess potential impact: If the PTAB institutes trial on any claims, it significantly weakens the patent owner's position regarding those claims. If institution is denied, it strengthens the patent owner's position for the challenged claims against similar prior art.

Inventors

• Andrei Golman: Likely Intone Inc. (assigned patent to Intone Inc. on filing date)
• Dmitrii Sadykov: Likely Intone Inc. (assigned patent to Intone Inc. on filing date)

Both inventors assigned their interest to Intone Inc. on the filing date of the application (December 19, 2022), which is a common practice for employees assigning intellectual property to their employer.

Original assignee

The original assignee named on the patent application filing was Intone Inc.

It is unclear whether Intone Inc. shipped a product embodying the claims. The patent details a technology for real-time accent correction in speech audio signals. Intone Inc. later assigned the patent to Sanas.ai Inc., which is active in this field. This suggests Intone Inc. may have been a startup or entity that developed the core technology.

Intone Inc.'s primary line of business, as inferred from the patent, was related to speech audio processing technology, particularly real-time accent correction.

Intone Inc. is no longer the assignee of record, having assigned the patent to Sanas.ai Inc. Its current operational status (operating, dissolved, acquired, etc.) is not determinable from the patent text alone, but the assignments suggest a transfer of assets.

Assignment timeline

Due to the inability to access the live USPTO Patent Assignment Search database at assignmentcenter.uspto.gov, the following assignment timeline is constructed using the "Legal status" -> "reassignment" events listed on Google Patents for US11715457. This means critical information such as specific reel/frame numbers and the correspondent of record (attorney/firm who filed the recording), which are essential for identifying NPE patterns, cannot be provided.

• 2022-12-19 (executed) / recorded 2022-12-19 (implied from patent filing date and assignment event)

  • Conveyance: Assignment of Assignors Interest
  • Assignor: SADYKOV, Dmitrii, GOLMAN, Andrei
  • Assignee: Intone Inc.
  • Correspondent: Not determinable from available information.
  • Context: Original assignment from inventors to founding company.

• 2025-01-16 (executed) / recorded 2025-01-16 (implied)

  • Conveyance: Assignment of Assignors Interest
  • Assignor: INTONE, INC.
  • Assignee: Sanas.ai Inc.
  • Correspondent: Not determinable from available information.
  • Context: Transfer of patent assets from original assignee to Sanas.ai Inc.

• 2025-06-06 (executed) / recorded 2025-06-06 (implied)

  • Conveyance: Assignment of Assignors Interest
  • Assignor: INTONE, INC.
  • Assignee: Sanas.ai Inc.
  • Correspondent: Not determinable from available information.
  • Context: Subsequent transfer of patent assets from original assignee to Sanas.ai Inc. (potentially a duplicate record, a corrective assignment, or part of a larger transaction).

Timeline diagram

timeline
    title Ownership of US 11715457
    2022 : Filed by Intone Inc
         : Inventors assigned to Intone
    2023 : Patent issued
    2025 : Assigned to Sanas.ai Inc
         : Assigned to Sanas.ai Inc
    2026 : IPR case IPR2026-00275 filed

NPE / troll-pattern signals

1. Shell-entity transfer — Unclear. Without correspondent addresses and more detailed corporate information for Intone Inc., it's not possible to determine if it was a shell entity. Sanas.ai Inc. appears to be an operating company based on its public profile.
2. Known asserter in the chain — Not present. Neither Intone Inc. nor Sanas.ai Inc. appear on common public NPE lists.
3. Repeat correspondent across the chain — Unclear. This information is not available from the Google Patents legal events. Access to the USPTO Assignment Center records is required to identify correspondents.
4. Cascading transfers — Not present. There are two assignments from Intone Inc. to Sanas.ai Inc. in 2025, but they are spaced several months apart, and without correspondent information, it's not possible to determine if they are "cascading" in a way indicative of an NPE pattern.
5. Pre-litigation transfer — Unclear. The first district court litigation (3:25-cv-05666) was filed in 2025. The patent was assigned to Sanas.ai Inc. on 2025-01-16 and 2025-06-06. If the litigation was filed later in 2025, it could indicate a pre-litigation transfer. However, without a precise litigation filing date, it is unclear if the transfer dates fall within 6 months before the first infringement suit.
6. Bankruptcy fire-sale — Not present. There is no indication in the patent records or available information that Intone Inc. or Sanas.ai Inc. underwent bankruptcy proceedings leading to the patent transfer.
7. Privateering — Not present. No evidence suggests an operating company transferred the patent to an NPE for assertion on its behalf. Sanas.ai Inc. is the current assignee and appears to be an operating company.
8. Defensive aggregator (anti-NPE) — Not present. The chain does not terminate at a known defensive aggregator like RPX or AST.

Verdict

Insufficient data

The lack of access to the USPTO Assignment Center records means critical information, particularly correspondent details and precise recording dates, is missing. This prevents a thorough analysis of NPE signals such as shell-entity transfers and repeat correspondents. While the current assignee, Sanas.ai Inc., appears to be an operating company, the absence of full assignment data makes a confident determination of NPE patterns impossible at this time.

For verification of assignment records, please refer to the USPTO Assignment Center: https://assignmentcenter.uspto.gov/

To identify the most relevant prior art for US patent 11715457, a search of the USPTO database for the specific patent number 11715457 would be necessary. The provided text from Google Patents lists "Prior art keywords" but does not detail specific patent citations considered as prior art during the examination of US11715457B1. Without direct access to the USPTO's official patent examination records or a comprehensive list of "References Cited" from the patent document itself (which is not fully provided in the prompt), it's not possible to definitively identify the "most relevant prior art" as determined by the patent examiner, nor can I provide the full citation, publication/filing date, brief description, and specific claims potentially anticipated under 35 U.S.C. § 102 for each reference.

The current task requires searching the USPTO database. However, as an AI, I do not have direct, real-time access to the USPTO's Patent Public Search tool or its internal databases to conduct this specific type of search as of April 26, 2026. While the USPTO website offers Patent Public Search, this is a web-based application requiring direct user interaction.

Therefore, I cannot fulfill the request to identify the most relevant prior art by searching the USPTO database for patent 11715457 and providing the detailed analysis for each cited reference.

The provided text for US Patent 11,715,457 B1, specifically under the "Prior art" section, lists "Prior art keywords" (audio signal, features, chunk, speech audio, chunks) and a "Prior art date" (2022-01-10). However, it does not include a list of specific prior art references (e.g., patent numbers, journal articles, or other publications) that can be identified and combined for an obviousness analysis under 35 U.S.C. § 103.

Without specific prior art documents, it is not possible to:

1. Identify concrete combinations of references.
2. Explain why a person having ordinary skill in the art would have been motivated to combine those specific references.

The "Background" section of the patent generally notes that "Existing solutions for correcting accent in audio signals are not very effective in real-time conversations." This statement acknowledges the existence of prior art in accent correction, but implies that these solutions did not adequately address the real-time processing challenge with low latency. However, this general statement does not provide the specific technical details of these prior art solutions necessary for a § 103 analysis involving combinations.

Therefore, I cannot fulfill the request to identify combinations of prior art references that would render the claims obvious, as the authoritative patent text provided does not enumerate specific prior art references.