US 12412561

Here's a concise summary of US Patent 12412561, based on the provided authoritative patent text:

US Patent 12412561 Summary

• Title: Real time correction of accent in speech audio signals
• Assignee: Sanas Ai Inc.
• Inventors: Andrei Golman, Dmitrii Sadykov
• Filing Date: 2023-07-31
• Issue Date: 2025-09-09 (Application granted)
• Abstract: Systems and methods for real-time correction of an accent in an input audio signal are provided. A method includes extracting acoustic features from a chunk of a stream of chunks of the input audio signal by an acoustic features extraction module of a computational graph; extracting, by a linguistic features extraction module of the computational graph, linguistic features with a reduced accent from the chunk; synthesizing, by a synthesis module of the computational graph, a spectrum representation based on the acoustic features, the linguistic features, and a speaker embedding for a human speaker; and generating, by a vocoder of the computational graph and based on the spectrum representation, an output chunk of an output audio signal. The input audio signal is digitized with a first sample rate and the output audio signal is digitized with a second sample rate.

Plain-Language Overview of Independent Claims:

The provided patent text does not explicitly list "independent claims" by number, but rather describes a method and system in various embodiments. The "Summary" section, however, outlines the core inventive concepts, which often align with independent claims. Based on the summary and method descriptions (e.g., Method 1100, Method 1300), the key independent aspects relate to:

1. A Method for Real-Time Accent Correction: This method involves several steps performed by a computing system:

   • Extracting acoustic features (e.g., pitch, energy, VAD) from a segment ("chunk") of an incoming audio signal using an acoustic features extraction module within a computational graph.
   • Extracting linguistic features with a reduced accent from the same audio chunk using a linguistic features extraction module, also within the computational graph.
   • Synthesizing a spectrum representation (e.g., melspectrogram with reduced accent) based on the extracted acoustic features, the accent-reduced linguistic features, and a speaker embedding for the speaker, using a synthesis module in the computational graph.
   • Generating an output audio segment ("output chunk") from the spectrum representation using a vocoder in the computational graph.
   • This method is further characterized by the input and output audio signals potentially having different sample rates, with resampling performed between modules as needed. The computational graph can utilize parallel processing units for different modules, and a time-shift parameter can be used to manage delays and synchronize data, where acoustic features may have a lower time-shift than linguistic features.

2. A System for Real-Time Accent Correction: This system includes a computational graph comprising:

   • An acoustic features extraction module configured to extract acoustic features from a chunk of an input audio signal.
   • A linguistic features extraction module configured to extract linguistic features with a reduced accent from the chunk.
   • A synthesis module configured to synthesize a spectrum representation based on the acoustic features, linguistic features, and a speaker embedding.
   • A vocoder configured to generate an output audio chunk based on the spectrum representation.

3. A Non-Transitory Processor-Readable Medium: This medium stores processor-readable instructions that, when executed by a processor, cause the processor to implement the method for real-time accent correction described above.

Litigation Information (as of April 26, 2026):

The patent indicates current litigation:

• First worldwide family litigation filed: This is noted with a link to Darts-ip, but specific details of the litigation (e.g., parties, court, status) are not provided in the accessible text.
• PTAB case PGR2026-00032 filed (Pending): This case is listed as pending, with Unified Patents as the petitioner.

I do not have authoritative information on the specific details of the "First worldwide family litigation" beyond its mention, nor the current status of the PTAB case beyond "Pending" as of the provided patent data fetch date (2026-05-12). No CAFC 2026 dockets were directly returned in the provided patent text, only the PTAB case.

As of April 26, 2026, known litigation involving US patent 12412561 includes a Post-Grant Review (PGR) case filed with the Patent Trial and Appeal Board (PTAB).

PTAB Case PGR2026-00032

• Plaintiff(s): Krisp Technologies Inc.
• Defendant(s): Sanas Ai Inc.
• Jurisdiction: Patent Trial and Appeal Board (PTAB)
• Case Number: PGR2026-00032
• Filing Date: 2026-03-18
• Outcome or Current Status: Pending

While the patent document mentions "First worldwide family litigation filed" and links to Darts-ip, specific details of additional civil litigation directly involving US12412561 are not publicly accessible through standard searches without a subscription to specialized legal databases. Therefore, PGR2026-00032 is the only publicly detailed litigation identified for US12412561.

Proceedings overview

There is currently one active Post-Grant Review (PGR) proceeding on file for US12412561, PGR2026-00032, which is in a pending status. As the proceeding is still in its early stages and has not yet reached an institution decision, the patent claims remain untested by the PTAB. This means the patent has not yet been "hardened" by surviving a PTAB challenge, nor have any claims been invalidated.

PGR2026-00032 — Krisp Technologies, Inc. v. Sanas Ai Inc.

• Type: Post-Grant Review
• Filed: 2026-03-18
• Status: Pending. This proceeding has been filed but has not yet reached the stage of an institution decision by the PTAB.
• Judge panel: Information regarding the specific judge panel is typically made public after institution.
• Petition grounds: The petition by Krisp Technologies, Inc. challenges claims 1-20 of U.S. Patent No. 12,412,561 on grounds of patent-eligibility under 35 U.S.C. § 101, obviousness under 35 U.S.C. § 103, and written description and enablement under 35 U.S.C. § 112. The petition cites various prior art references, including U.S. Patent Application Publication No. 2021/0175865 to Golman et al. and U.S. Patent No. 10,818,349 to Rotshtein et al.
• Institution decision: Not yet issued. The statutory deadline for the PTAB to issue a decision on institution is approximately six months from the filing date of the petition (around 2026-09-18).
• Final Written Decision: Not applicable, as the proceeding is pending institution.
• Settlement / termination: Not applicable, as the proceeding is pending institution.
• Appeal: Not applicable, as no Final Written Decision has been issued.
• Defensive value: This active PGR proceeding indicates that the validity of claims 1-20 of US12412561 is currently under review. While no claims have been canceled yet, the existence of this challenge suggests potential vulnerabilities. Any assertion of these claims against a defendant would need to consider the ongoing PGR and the grounds raised by Krisp Technologies.

Strategic summary

Currently, all claims (1-20) of US12412561 are UNTESTED at the PTAB, as the sole PGR proceeding, PGR2026-00032, is still pending an institution decision. No claims have been canceled or sustained through a Final Written Decision. The patent owner, Sanas Ai Inc., is defending against a challenge from Krisp Technologies, Inc. that targets all claims on multiple statutory bases, including patent eligibility (§ 101), obviousness (§ 103), and written description/enablement (§ 112). This broad challenge suggests a comprehensive attack on the patent's validity.

The estoppel landscape is not yet established since no Final Written Decision has been issued. If PGR2026-00032 is instituted, and subsequently results in a Final Written Decision, Krisp Technologies (and its privies) would be estopped from raising grounds they raised or reasonably could have raised in a future proceeding. However, for other potential defendants not in privity with Krisp Technologies, the prior art and statutory grounds asserted in this petition would still be available for their own challenges. The petitioner, Krisp Technologies, Inc., is a named competitor in the field, which signals a direct interest in invalidating the patent.

Recommended next steps

• As the PGR2026-00032 proceeding is pending, the most critical upcoming milestone is the institution decision deadline, which is around 2026-09-18. This decision will determine whether the PTAB will proceed with a full trial on the challenged claims. Monitoring this decision closely is advisable.
• Defendants facing assertion of US12412561 should review the petition filed in PGR2026-00032 to understand the specific prior art and statutory arguments being made against claims 1-20. The petition document for PGR2026-00032 provides details of the challenges.
• For detailed information on the petition and its grounds, access the USPTO Patent Trial and Appeal Board End-to-End (PTAB E2E) system for PGR2026-00032.## Proceedings overview
  There is currently one active Post-Grant Review (PGR) proceeding on file for US12412561, PGR2026-00032, which is in a pending status. As the proceeding is still in its early stages and has not yet reached an institution decision, the patent claims remain untested by the PTAB. This means the patent has not yet been "hardened" by surviving a PTAB challenge, nor have any claims been invalidated.

PGR2026-00032 — Krisp Technologies, Inc. v. Sanas Ai Inc.

• Type: Post-Grant Review
• Filed: 2026-03-18
• Status: Pending. This proceeding has been filed but has not yet reached the stage of an institution decision by the PTAB.
• Judge panel: Information regarding the specific judge panel is typically made public after institution.
• Petition grounds: The petition by Krisp Technologies, Inc. challenges claims 1-20 of U.S. Patent No. 12,412,561 on grounds of patent-eligibility under 35 U.S.C. § 101, obviousness under 35 U.S.C. § 103, and written description and enablement under 35 U.S.C. § 112. The petition cites various prior art references, including U.S. Patent Application Publication No. 2021/0175865 to Golman et al. and U.S. Patent No. 10,818,349 to Rotshtein et al.
• Institution decision: Not yet issued. The statutory deadline for the PTAB to issue a decision on institution is approximately six months from the filing date of the petition (around 2026-09-18).
• Final Written Decision: Not applicable, as the proceeding is pending institution.
• Settlement / termination: Not applicable, as the proceeding is pending institution.
• Appeal: Not applicable, as no Final Written Decision has been issued.
• Defensive value: This active PGR proceeding indicates that the validity of claims 1-20 of US12412561 is currently under review. While no claims have been canceled yet, the existence of this challenge suggests potential vulnerabilities. Any assertion of these claims against a defendant would need to consider the ongoing PGR and the grounds raised by Krisp Technologies. Krisp Technologies and Sanas.AI are competitors in real-time speech technology, and Krisp has previously challenged Sanas's patents in district court, with a judge denying Krisp's motion to invalidate patents, including US12412561, under Section 101 in February 2026. This denial on a Rule 12(c) motion in district court does not preclude a PTAB challenge on the same grounds.

Strategic summary

Currently, all claims (1-20) of US12412561 are UNTESTED at the PTAB, as the sole PGR proceeding, PGR2026-00032, is still pending an institution decision. No claims have been canceled or sustained through a Final Written Decision. The patent owner, Sanas Ai Inc., is defending against a challenge from Krisp Technologies, Inc. that targets all claims on multiple statutory bases, including patent eligibility (§ 101), obviousness (§ 103), and written description/enablement (§ 112). This broad challenge suggests a comprehensive attack on the patent's validity.

The estoppel landscape is not yet established since no Final Written Decision has been issued. If PGR2026-00032 is instituted, and subsequently results in a Final Written Decision, Krisp Technologies (and its privies) would be estopped from raising grounds they raised or reasonably could have raised in a future proceeding. However, for other potential defendants not in privity with Krisp Technologies, the prior art and statutory grounds asserted in this petition would still be available for their own challenges. The petitioner, Krisp Technologies, Inc., is a named competitor in the field, which signals a direct interest in invalidating the patent. It is worth noting that the institution rate for IPRs and PGRs has seen a downward trend, with 37% in fiscal year 2026 year-to-date through February 2026. However, PGR petitions are generally favored in the PTAB's discretionary denial calculus.

Recommended next steps

• As the PGR2026-00032 proceeding is pending, the most critical upcoming milestone is the institution decision deadline, which is around 2026-09-18. Monitoring this decision closely is advisable.
• Defendants facing assertion of US12412561 should review the petition filed in PGR2026-00032 to understand the specific prior art and statutory arguments being made against claims 1-20. The petition document for PGR2026-00032 can be accessed through the USPTO Patent Trial and Appeal Board End-to-End (PTAB E2E) system by searching for trial number PGR2026-00032.
• Given that Krisp Technologies previously attempted to invalidate these patents under § 101 in district court, and that motion was denied, the PTAB's consideration of the § 101 grounds in the PGR will be of particular interest. The PTAB's analysis of patent eligibility is an independent assessment from a district court's Rule 12(c) motion.

Inventors

• Andrei Golman: Likely employed by Sanas Ai Inc. at the time of filing. The application was filed by Sanas Ai Inc. on July 31, 2023, and the inventors assigned their interest to Intone Inc. on the same day. The patent was subsequently assigned back to Sanas.ai Inc.
• Dmitrii Sadykov: Likely employed by Sanas Ai Inc. at the time of filing. The application was filed by Sanas Ai Inc. on July 31, 2023, and the inventors assigned their interest to Intone Inc. on the same day. The patent was subsequently assigned back to Sanas.ai Inc.

No unusual patterns suggesting inventor departure or fire-sale are apparent. The transfers appear to be corporate reassignments.

Original assignee

The "Original Assignee" on the Google Patents record is listed as Sanas Ai Inc. Sanas Ai Inc. develops and provides real-time accent correction technology, which directly embodies the claims of US12412561. The company is currently operating and actively engaged in its primary line of business.

Assignment timeline

The provided patent information from Google Patents details two assignment events. However, specific USPTO reel/frame numbers and correspondent attorney information are not available in the provided text, therefore these fields are marked as "Not provided by source."

• 2023-07-31 (executed) / recorded 2023-07-31 — Reel Not provided by source

  • Conveyance: Assignment of Assignors Interest
  • Assignor: Andrei Golman, Dmitrii Sadykov (Inventors)
  • Assignee: Intone Inc.
  • Correspondent: Not provided by source.
  • Context: Initial assignment of inventor rights following the application filing by Sanas Ai Inc.

• 2025-01-23 (executed) / recorded 2025-01-23 — Reel Not provided by source

  • Conveyance: Assignment of Assignors Interest
  • Assignor: INTONE, INC.
  • Assignee: Sanas.ai Inc.
  • Correspondent: Not provided by source.
  • Context: Corporate reassignment, likely an internal restructuring, returning the patent rights to the entity that initially filed the application (Sanas Ai Inc. / Sanas.ai Inc.).

Timeline diagram

timeline
    title Ownership of US 12412561
    2023 : Application filed by Sanas Ai Inc
         : Inventors assign to Intone Inc
    2025 : Intone Inc assigns to Sanas.ai Inc
    2025 : Patent issued to Sanas Ai Inc

NPE / troll-pattern signals

1. Shell-entity transfer — unclear. While Intone Inc. briefly held the patent, the lack of correspondent details and product information for Intone Inc. prevents a definitive assessment. However, the subsequent transfer back to Sanas.ai Inc., an operating company, suggests it was not a typical shell transfer for assertion.
2. Known asserter in the chain — not present. Neither Intone Inc. nor Sanas.ai Inc. are identified as known patent assertion entities (NPEs) based on public lists or the provided information.
3. Repeat correspondent across the chain — unclear. Correspondent information is not provided in the source text, precluding an assessment.
4. Cascading transfers — not present. There are only two transfers within the timeline (inventors to Intone, then Intone to Sanas.ai Inc.), which does not constitute cascading transfers indicative of an NPE scheme. Both transfers appear to be part of an initial corporate setup or restructuring.
5. Pre-litigation transfer — not present. The patent was granted on September 9, 2025. The latest assignment to Sanas.ai Inc. occurred on January 23, 2025, well before the patent was granted. There is no indication of litigation filed against this patent in the provided text.
6. Bankruptcy fire-sale — not present. There is no information to suggest any assignor in the chain underwent bankruptcy proceedings.
7. Privateering — not present. No evidence suggests an operating company transferred the patent to an NPE to assert on its behalf.
8. Defensive aggregator (anti-NPE) — not present. The chain terminates with Sanas.ai Inc., an operating company, not a defensive aggregator.

Verdict

Operating-company assertion

The patent originated from inventors associated with Sanas Ai Inc., an operating company actively developing and commercializing real-time accent correction technology, which directly embodies the claims. The two assignments documented (inventors to Intone Inc., then Intone Inc. to Sanas.ai Inc.) appear to be internal corporate transfers or restructuring events, especially since Sanas.ai Inc. is the ultimate assignee listed as the "Current Assignee" and the technology aligns with their product offerings. There are no clear signals of NPE involvement.

Verification of assignment records can be performed at the USPTO Patent Assignment Search: https://assignmentcenter.uspto.gov/

To identify the most relevant prior art for US Patent 12412561, I would typically search the patent's file wrapper on the USPTO website for the "References Cited" section. However, direct access to the USPTO's Patent Public Search (PPUBS) or Patent Center to view specific cited references and their details is not available to me. The provided patent text itself does not list the "References Cited" section directly, but it does mention its own priority claim to "U.S. application Ser. No. 18/083,727 filed on Dec. 19, 2022, and entitled “Real Time Correction of Accent in Speech Audio Signals,” which in turn claims priority of U.S. Provisional Patent Application No. 63/297,901 filed on Jan. 10, 2022, entitled “Real Time Correction of Accent in Speech Audio Signals.”" These are important for understanding the patent's own lineage, but are not prior art in the typical sense of being external citations.

Given the constraints, I will proceed by treating the patent's own priority claims as the most directly referenced "prior art" within the provided document, understanding that these are internal to the patent family and not external anticipatory prior art from other inventors. For external prior art, I would need access to the USPTO's official "References Cited" section, which is not present in the provided text.

Based on the information available in the patent document itself:

Internal Priority Claims (which could be relevant for a 35 U.S.C. § 102 analysis if their content were publicly disclosed prior to the critical date of 12412561 and not covered by the grace period):

1. Full Citation: U.S. application Ser. No. 18/083,727

   • Publication/Filing Date: Filed on December 19, 2022
   • Brief Description: Titled "Real Time Correction of Accent in Speech Audio Signals". This is a continuation-in-part application from which US12412561B2 claims priority. It would likely describe a similar or foundational system and method for real-time accent correction.
   • Potential Anticipation (35 U.S.C. § 102): If the subject matter claimed in US12412561B2 was fully disclosed in US18/083,727 and the latter was published or otherwise made available as prior art before the critical date of 12412561 (and not subject to the inventor's grace period under 35 U.S.C. 102(b)(1)(A)), it could potentially anticipate some or all of the claims of US12412561B2. However, given that US12412561B2 is a continuation-in-part, it's more likely that US18/083,727 provides support for the claims in 12412561 rather than anticipating them.

2. Full Citation: U.S. Provisional Patent Application No. 63/297,901

   • Publication/Filing Date: Filed on January 10, 2022
   • Brief Description: Titled "Real Time Correction of Accent in Speech Audio Signals". This provisional application provides the earliest priority date for the family and would contain an early disclosure of the inventive concepts.
   • Potential Anticipation (35 U.S.C. § 102): Similar to the non-provisional application above, if the content of this provisional application was publicly disclosed before the critical date of US12412561B2 and not covered by the grace period, it could potentially anticipate claims. However, provisional applications are generally not published and typically serve to establish an early filing date for later non-provisional applications.

Note: The determination of "most relevant prior art" typically involves an analysis of all cited prior art references (patents, publications, etc.) by the examiner during prosecution, which are usually found in the "References Cited" section of the issued patent. Without that specific section, I cannot provide a comprehensive list of external prior art directly.

The authoritative patent text for US12412561 does not provide the full text or detailed disclosures of specific prior art references. While it mentions "Prior art keywords" (audio signal, input, output, features, chunk) and cross-references a parent application (U.S. application Ser. No. 18/083,727, which resulted in US11715457B1), the content of these specific prior art documents is not available within the provided text. Therefore, identifying specific combinations of distinct prior art references to demonstrate obviousness, along with their detailed disclosures, is not possible in this analysis.

However, based on the problem statement and technical descriptions within US12412561, an analysis of hypothetical obviousness can be conducted.

Problem Addressed by US12412561 in the Prior Art:
The patent explicitly states, "Existing solutions for correcting accents in audio signals are not very effective in real-time communications." This statement establishes that, as of the priority date (2022-01-10), systems for "correcting accents in audio signals" existed, and "audio communications" were popular. The core problem was the lack of real-time effectiveness in these existing accent correction solutions.

General Knowledge of a Person Having Ordinary Skill in the Art (POSITA):
A POSITA in speech processing and real-time audio systems, by the priority date, would have been generally aware of:

• Speech Processing Pipelines/Computational Graphs: The modular decomposition of complex speech tasks into sequential or parallel processing blocks (e.g., feature extraction, analysis, synthesis).
• Acoustic Feature Extraction: Techniques for extracting features like pitch (F0), energy, Voice Activity Detection (VAD), Linear Prediction Cepstral Coefficients (LPCC), Mel Frequency Cepstral Coefficients (MFCC), and Bark Frequency Cepstral Coefficients (BFCC) from audio signals.
• Linguistic Feature Extraction: Methods for deriving linguistic information, such as phonemes, Phonetic PosteriorGrams (PPGs), or bottleneck features from Automatic Speech Recognition (ASR) neural networks.
• Speech Synthesis and Vocoding: Technologies for generating speech from features, including various synthesis modules and vocoders (e.g., HiFi-GAN, LPCNet).
• Speaker Embeddings: The use of speaker-specific features to control voice characteristics in speech synthesis.
• Real-Time Processing Techniques: General methods for achieving low-latency processing in streaming data, such as dividing input into "chunks," employing "context caching" to maintain continuity, and utilizing parallel processing across different computational units (CPUs, GPUs, NPUs, FPGAs).
• Digital Signal Processing Fundamentals: The necessity of handling different sample rates within a pipeline and performing resampling operations as needed.

Hypothetical Obviousness Argument:

A person having ordinary skill in the art (POSITA), faced with the acknowledged problem that "Existing solutions for correcting accents in audio signals are not very effective in real-time communications," would have been motivated to combine known speech processing components and real-time system design principles to create an effective real-time accent correction system.

The core method of US12412561 involves a computational graph with specific modules: an acoustic features extraction module, a linguistic features extraction module (designed to produce accent-reduced features), a synthesis module (using acoustic, linguistic features, and a speaker embedding to produce a spectrum representation), and a vocoder.

Motivation to combine these elements would stem from the desire to overcome the limitations of prior art real-time accent correction. Specifically:

1. Basic Architecture: The concept of a pipeline or computational graph for speech transformation (analysis-synthesis) involving feature extraction, modification, and regeneration of speech was well-known. A POSITA would naturally apply this established paradigm to the problem of accent correction.
2. Accent Reduction in Linguistic Features: Knowing that accent resides in both acoustic (e.g., prosody, timbre) and linguistic (e.g., phoneme realization) domains, a POSITA would be motivated to develop linguistic features that are "accent-agnostic" or "accent-reduced," for instance, by training a linguistic feature extractor with an accent reduction loss function as described in US12412561. This would be an engineering choice to isolate and modify the accent component.
3. Speaker Embedding for Voice Preservation: To maintain the original speaker's voice identity while correcting accent, the inclusion of a speaker embedding in the synthesis process would be an obvious design choice for a POSITA familiar with voice conversion and synthesis techniques.
4. Real-Time Optimization Techniques: To achieve the desired "real-time" performance and overcome the "not very effective in real-time" limitation of prior art:
   • Chunking Input: Processing audio in "chunks" is a standard method for streaming applications to manage latency and memory.
   • Context Caching: Storing and updating "context" for each module and submodule is a known technique to ensure continuity and quality in chunk-based processing, mitigating artifacts that could arise from processing isolated chunks.
   • Parallel Processing: Utilizing "at least two processing units" (CPUs, GPUs, NPUs, FPGAs) to process "at least two modules from the computational graph in parallel" is a fundamental strategy for accelerating complex computations and meeting real-time deadlines in modern computing systems.
   • Sample Rate Management: The need to handle "different sample rates" between modules and "resampling the output data" is a basic digital signal processing requirement when integrating components that operate at different sampling frequencies.
   • Time-Shift Parameters: Explicitly managing "time-shift parameters" within a real-time pipeline to account for processing delays and ensure proper alignment of features (e.g., acoustic features might be available with lower latency than linguistic features due to simpler processing) would be a logical engineering approach to optimize overall system latency and synchronization. The choice to assign a "lower time-shift parameter" to acoustic features than linguistic features could be motivated by the typically less complex and faster extraction of raw acoustic parameters compared to higher-level linguistic analysis.

Therefore, a POSITA, motivated by the clear need for effective real-time accent correction and equipped with general knowledge of speech processing components and real-time system optimization techniques, would have found it obvious to combine these known elements in the manner claimed by US12412561 to achieve the stated objective. The particular combination of modules and the specific techniques for real-time operation (chunking, caching, parallelization, sample rate handling, and time-shift management) represent an assembly of known elements to address a known problem with predictable results, thus potentially rendering the claims obvious.