Skip to main content
TencentPatent grant

Tencent was granted a patent for training speech-conversion models.

Source: Autobound Signal API · 108 signals tracked for Tencent · updated

Get Tencent's live signals in Claude or ChatGPT, or by API

AskWhat changed at Tencent this week? Use Autobound signals for tencent.com.

What happened

In November 2026 Tencent patented technology for converting spoken accents, with applications in voice interfaces, speech tools, and other audio-AI systems.

Source

Abstract

This application discloses a speech conversion method performed by a computer device. The method includes: obtaining first accent audio corresponding to a first accent; extracting a first content feature from the first accent audio through the first ASR model, the first content feature being corresponding to the first accent; converting the first content feature into a second content feature through the second conversion model, the second content feature being corresponding to a second accent; and performing audio conversion on the second content feature through the third conversion model to obtain second accent audio.

patents.google.com/patent/US12802698Read the full source

Extracted by Autobound

From the Signal API record
Signal
Patent grant

What this signalsA new patent often shows where a company is putting its R&D budget.

Grant date
Nov 17, 2026
Inventors
Peiji Yang
Tech area
speech / audio AI
Patent number
US12802698

The full record

From the Signal API record

People

  • Peiji YangInventor

Details

Primary CPC class
G10L 21/007 (Speech analysis or synthesis; speech/voice recognition; audio coding)
USPTO assignee
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
What the invention does
A training method that recognizes the words in speech from one accent and transforms their content features to represent another accent.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Language Technology
  • Voice Technology

Technologies named

  • speech conversion
  • automatic speech recognition
  • audio AI

Extraction

Detected
Nov 18, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Tencent and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at Tencent this week?”

  2. Send it to your own tools

    The Signal API returns patent signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full patents-company record in the Signal API and MCP can also have these 8 fields. Some fields are empty for some signals.

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API
Show the full JSONThe record on this page and the API request

GET /v1/signals/07ce0062-2c85-5e04-adde-84b9abefdd75 returns this record as JSON. POST /v1/companies/enrich returns every signal for tencent.com.

{
  "signal_id": "07ce0062-2c85-5e04-adde-84b9abefdd75",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-11-18T15:41:55+00:00",
  "company": {
    "name": "Tencent",
    "domain": "tencent.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G10L 21/007",
        "label": "Speech analysis or synthesis; speech/voice recognition; audio coding"
      },
      {
        "code": "G10L 15/02",
        "label": "Speech analysis or synthesis; speech/voice recognition; audio coding"
      },
      {
        "code": "G10L 15/063",
        "label": "Speech analysis or synthesis; speech/voice recognition; audio coding"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Language Technology",
      "Voice Technology"
    ],
    "detail": "In November 2026 Tencent patented technology for converting spoken accents, with applications in voice interfaces, speech tools, and other audio-AI systems.",
    "summary": "Tencent was granted a patent for training speech-conversion models.",
    "event_at": "2026-11-17",
    "inventors": [
      {
        "name": "Peiji Yang",
        "status": "unresolved",
        "is_primary": true
      }
    ],
    "tech_area": "speech / audio AI",
    "event_kind": "grant_date",
    "grant_date": "2026-11-17",
    "source_url": "https://patents.google.com/patent/US12802698",
    "cpc_primary": {
      "code": "G10L 21/007",
      "label": "Speech analysis or synthesis; speech/voice recognition; audio coding"
    },
    "patent_title": "Method and apparatus for training speech conversion model, device, and medium",
    "patent_number": "US12802698",
    "uspto_assignee": "TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED",
    "patent_abstract": "This application discloses a speech conversion method performed by a computer device. The method includes: obtaining first accent audio corresponding to a first accent; extracting a first content feature from the first accent audio through the first ASR model, the first content feature being corresponding to the first accent; converting the first content feature into a second content feature through the second conversion model, the second content feature being corresponding to a second accent; and performing audio conversion on the second content feature through the third conversion model to obtain second accent audio.",
    "precision_class": "structural",
    "invention_explanation": "A training method that recognizes the words in speech from one accent and transforms their content features to represent another accent.",
    "technologies_mentioned": [
      "speech conversion",
      "automatic speech recognition",
      "audio AI"
    ]
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.