Skip to main content
BaiduPatent grant

Baidu was granted a patent for AI-generated audio from text.

Source: Autobound Signal API · 90 signals tracked for Baidu · updated

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

AskWhat changed at Baidu this week? Use Autobound signals for baidu.com.

What happened

In November 2026 Baidu patented a text-to-audio system for creating synthesized speech and other audio in AI applications.

Source

Abstract

An audio generation method, a method of training an audio generation model, an electronic device, and a storage medium, which relate to a field of an artificial intelligence technology, in particular to fields of deep learning, large model and audio synthesis technologies. The audio generation method includes: fusing a target phoneme feature of a target text and a target semantic feature of the target text to obtain a target fusion feature; obtaining an encoding feature according to the target fusion feature, a reference fusion feature and a reference audio feature, where the reference fusion feature is obtained by fusing a reference phoneme feature of a reference text and a reference semantic feature of the reference text, and the reference audio feature is determined according to a reference audio corresponding to the reference text; and decoding the encoding feature to obtain a target audio corresponding to the target text.

patents.google.com/patent/US12802682Read 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
3
Tech area
speech / audio AI
Patent number
US12802682

The full record

From the Signal API record

People

  • Huihui HeInventor
  • Leyi WangInventor
  • Minghao LiuInventor

Details

Primary CPC class
G10L 13/08 (Speech analysis or synthesis; speech/voice recognition; audio coding)
USPTO assignee
BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
What the invention does
A model combines the sounds of words with their meaning before generating audio, helping produce speech that matches the input text.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Language Technology
  • Speech Recognition

Technologies named

  • text-to-speech
  • audio synthesis
  • deep learning
  • large language models

Extraction

Detected
Nov 18, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Baidu 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 Baidu 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/05df94ce-3e74-5d24-ab1e-320dfe56df79 returns this record as JSON. POST /v1/companies/enrich returns every signal for baidu.com.

{
  "signal_id": "05df94ce-3e74-5d24-ab1e-320dfe56df79",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-11-18T15:41:48+00:00",
  "company": {
    "name": "Baidu",
    "domain": "baidu.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G10L 13/08",
        "label": "Speech analysis or synthesis; speech/voice recognition; audio coding"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Language Technology",
      "Speech Recognition"
    ],
    "detail": "In November 2026 Baidu patented a text-to-audio system for creating synthesized speech and other audio in AI applications.",
    "summary": "Baidu was granted a patent for AI-generated audio from text.",
    "event_at": "2026-11-17",
    "inventors": [
      {
        "name": "Huihui He",
        "status": "unresolved",
        "is_primary": true
      },
      {
        "name": "Leyi Wang",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Minghao Liu",
        "status": "unresolved",
        "is_primary": false
      }
    ],
    "tech_area": "speech / audio AI",
    "event_kind": "grant_date",
    "grant_date": "2026-11-17",
    "source_url": "https://patents.google.com/patent/US12802682",
    "cpc_primary": {
      "code": "G10L 13/08",
      "label": "Speech analysis or synthesis; speech/voice recognition; audio coding"
    },
    "patent_title": "Audio generation method, method of training model, device, and storage medium",
    "patent_number": "US12802682",
    "uspto_assignee": "BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.",
    "patent_abstract": "An audio generation method, a method of training an audio generation model, an electronic device, and a storage medium, which relate to a field of an artificial intelligence technology, in particular to fields of deep learning, large model and audio synthesis technologies. The audio generation method includes: fusing a target phoneme feature of a target text and a target semantic feature of the target text to obtain a target fusion feature; obtaining an encoding feature according to the target fusion feature, a reference fusion feature and a reference audio feature, where the reference fusion feature is obtained by fusing a reference phoneme feature of a reference text and a reference semantic feature of the reference text, and the reference audio feature is determined according to a reference audio corresponding to the reference text; and decoding the encoding feature to obtain a target audio corresponding to the target text.",
    "precision_class": "structural",
    "invention_explanation": "A model combines the sounds of words with their meaning before generating audio, helping produce speech that matches the input text.",
    "technologies_mentioned": [
      "text-to-speech",
      "audio synthesis",
      "deep learning",
      "large language models"
    ]
  }
}

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.