ARXIV:2603.04219 · TEXT-TO-SPEECH · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

arXiv

ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.

Blocked on Code›Score6.0Evidence unverified

Opportunity summary

Pain ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training. While synthetic augmentation can provide linguistically rich and phonetically diverse speech, naively mixing large amounts of synthetic speech…

METHOD

Full abstract

We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis. While synthetic augmentation can provide linguistically rich and phonetically diverse speech, naively mixing large amounts of synthetic speech with limited real recordings often leads to speaker similarity degradation during fine-tuning. To address this issue, we propose ZeSTA, a simple domain-conditioned training framework that distinguishes real and synthetic speech via a lightweight domain embedding, combined with real-data oversampling to stabilize adaptation under extremely limited target data, without modifying the base architecture. Experiments on LibriTTS and an in-house dataset with two ZS-TTS sources demonstrate that our approach improves speaker similarity over naive synthetic augmentation while preserving intelligibility and perceptual quality.

RESULT

ScienceToStartup currently rates this 6.0/10 on the public viability pass. Experiments on LibriTTS and an in-house dataset with two ZS-TTS sources demonstrate that our approach improves speaker similarity over naive synthetic augmentation while preserving…

WHY NOW

Text-to-Speech moved forward this cycle; last verified April 2026. Public score 6.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score6.0

PainZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2603.04219 · TEXT-TO-SPEECH · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

arXiv

ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.

Blocked on Code›Score6.0Evidence unverified

Opportunity summary

Pain ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Text-to-Speech moved forward this cycle; last verified April 2026. Public score 6.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score6.0

PainZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2603.04219

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

unverified

0 refs; 0 sources; 17% coverage.

What was readable

linkedon filenot materializedderived fallback38 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

6.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Text-to-Speech moved forward this cycle; last verified April 2026. Public score 6.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training. While synthetic augmentation can provide linguistically rich and phonetically diverse speech, naively mixing large amounts of synthetic speech with limited real recordings often leads to speaker similarity degradation during fine-tuning.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis. While synthetic augmentation can provide linguistically rich and phonetically diverse speech, naively mixing large amounts of synthetic speech with limited real recordings often leads to speaker similarity degradation during fine-tuning.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 6.0/10 on the public viability pass. Experiments on LibriTTS and an in-house dataset with two ZS-TTS sources demonstrate that our approach improves speaker similarity over naive synthetic augmentation while preserving intelligibility and perceptual quality.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Text-to-Speech moved forward this cycle; last verified April 2026. Public score 6.0/10.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

Text-to-Speech

Competitors

not indexed

Competitive landscape

ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.

Segment

Text-to-Speech

Adoption evidence

No public code link in the paper record yet

Commercial read

6.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2603.04219 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(38)

Zero-Shot TTS With Enhanced Audio Prompts: Bsc Submission For The 2026 Wildspoof Challenge TTS Track

2026José Giraldo, Alex Peir'o-Lilja et al.

Data Augmentation using Speech Synthesis for Speaker-Independent Dysarthria Severity Classification

2025Minseo Kim, Minsu Han et al.

Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment

2025Xueyao Zhang, Yuancheng Wang et al.

Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement

2025Jae-Sung Bae, Anastasia Kuznetsova et al.

CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

2024Zhihao Du, Yuxuan Wang et al.

Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis

2024Shijia Liao, Yuxuan Wang et al.

Leveraging Low-Rank Adaptation for Parameter-Efficient Fine-Tuning in Multi-Speaker Adaptive Text-to-Speech Synthesis

2024Changi Hong, Jung Hyuk Lee et al.

Zero Shot Text to Speech Augmentation for Automatic Speech Recognition on Low-Resource Accented Speech Corpora

2023Francesco Nespoli, Daniel Barreda et al.

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

2023Matt Le, Apoorv Vyas et al.

ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation

2023Ambuj Mehrish, Abhinav Ramesh Kashyap et al.

Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision

2023E. Kharitonov, Damien Vincent et al.

Robust Speech Recognition via Large-Scale Weak Supervision

2022Alec Radford, Jong Wook Kim et al.

Evaluating and reducing the distance between synthetic and real speech distributions

2022Christoph Minixhofer, Ondrej Klejch et al.

AudioLM: A Language Modeling Approach to Audio Generation

2022Zalán Borsos, Raphaël Marinier et al.

Low-data? No problem: low-resource, language-agnostic conversational text-to-speech via F0-conditioned data augmentation

2022Giulia Comini, Goeric Huybrechts et al.

TTS-by-TTS 2: Data-selective augmentation for neural speech synthesis using ranking support vector machine with variational autoencoder

2022Eunwoo Song, Ryuichi Yamamoto et al.

JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech

2022D. Lim, Sunghee Jung et al.

Cross-Speaker Style Transfer for Text-to-Speech Using Data Augmentation

2022M. Ribeiro, J. Roth et al.

HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis

2022Sang-Hoon Lee, Seung-bin Kim et al.

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

2021Edresson Casanova, Julian Weber et al.

Showing 20 of 38 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

none indexed

Extension

Builds On ThisTASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs

4.0

Builds On Thisdots.tts Technical Report

0.0

Builds On ThisProsodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input

5.0

Builds On ThisTest-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation

0.0

Commercially relevant

Higher ViabilityPilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis

8.0

Higher ViabilityAST: Adaptive, Seamless, and Training-Free Precise Speech Editing

7.0

Higher ViabilityEfficient ASR Training with Conversations that Never Happened

8.0

Higher ViabilityBoosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards

7.0

Higher ViabilityImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment

7.0

Higher ViabilityBTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs

7.0

Conflicting

none indexed

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2603.04219
Route: /paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis
Active tab: read
Artifact: zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis/paper-pack
REST build passport API/api/v1/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "dd5ca693-4414-4bdc-a460-d08b13790915",
  "arxiv_id": "2603.04219",
  "canonical_route": "/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis",
  "endpoints": {
    "paper_pack": "/api/v1/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis/paper-pack",
    "build_passport": "/api/v1/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis

stale

Proof freshness: stale
Proof status: unverified
Display score: 6/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

Canonical ID zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis | Route /paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2603.04219"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis",
  "normalized_query": "2603.04219",
  "route": "/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis",
  "paper_ref": "zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Watch and verify: ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

/buildability/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis

Watchwatch

Subject: ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis

Paper ref

zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis

arXiv id

2603.04219

Freshness

Generated at

2026-04-02T02:30:40.136Z

Evidence freshness

stale

Last verification

2026-04-02T02:30:40.136Z

Sources

References

Coverage

17%

Hash state

Lineage hash

a29893bd5f4b92ad2f5eec7a7bb3a9c0235ecef615790dbac6ceae2465e048fe

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: proof_status
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet
Unknown: proof verification has not been recorded yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis#webpage",
      "url": "https://sciencetostartup.com/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis",
      "name": "ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis",
      "description": "ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis#scholarlyArticle",
      "headline": "ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis",
      "description": "ZeSTA improves personalized speech synthesis by enhancing speaker similarity through zero-shot TTS augmentation and domain-conditioned training.",
      "url": "https://sciencetostartup.com/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis",
      "sameAs": "https://arxiv.org/abs/2603.04219",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2603.04219"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-03-04T16:04:02.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "fe57ef4a3f50dd43df25151ffedf6bb5ad4e0c89"
          },
          "url": "https://www.semanticscholar.org/paper/fe57ef4a3f50dd43df25151ffedf6bb5ad4e0c89"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "bba45e20888fac0b7f5d4c40e57e12d1190330c4"
          },
          "url": "https://www.semanticscholar.org/paper/bba45e20888fac0b7f5d4c40e57e12d1190330c4"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "78ad49d8e911cb5549c50cf77fd92febd144ba6e"
          },
          "url": "https://www.semanticscholar.org/paper/78ad49d8e911cb5549c50cf77fd92febd144ba6e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "47f446e24f8516859d7ce90873f0954b1851d601"
          },
          "url": "https://www.semanticscholar.org/paper/47f446e24f8516859d7ce90873f0954b1851d601"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a4f374a96e9d265a03e2e2cdd7e204e1e4e37416"
          },
          "url": "https://www.semanticscholar.org/paper/a4f374a96e9d265a03e2e2cdd7e204e1e4e37416"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3cc151df2a7f2b24df0dc5f3d439015b30fbe25c"
          },
          "url": "https://www.semanticscholar.org/paper/3cc151df2a7f2b24df0dc5f3d439015b30fbe25c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "b7f6afdd7eaed9200c69f57b44aad8b5b629b160"
          },
          "url": "https://www.semanticscholar.org/paper/b7f6afdd7eaed9200c69f57b44aad8b5b629b160"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a9e00c216ce69325a15fd139da0624978e54058a"
          },
          "url": "https://www.semanticscholar.org/paper/a9e00c216ce69325a15fd139da0624978e54058a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "2df789e62091d3e4868afc638d2dcb14d13165b9"
          },
          "url": "https://www.semanticscholar.org/paper/2df789e62091d3e4868afc638d2dcb14d13165b9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "071d021ef9dcd83686d7b12bec2e13283b2f048f"
          },
          "url": "https://www.semanticscholar.org/paper/071d021ef9dcd83686d7b12bec2e13283b2f048f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a02fbaf22237a1aedacb1320b6007cd70c1fe6ec"
          },
          "url": "https://www.semanticscholar.org/paper/a02fbaf22237a1aedacb1320b6007cd70c1fe6ec"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "da7c0e5afb152b35defb1ee6a6926503c648f36a"
          },
          "url": "https://www.semanticscholar.org/paper/da7c0e5afb152b35defb1ee6a6926503c648f36a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8c870bef01a4fbb20f60722ffc2f6bee3870b18b"
          },
          "url": "https://www.semanticscholar.org/paper/8c870bef01a4fbb20f60722ffc2f6bee3870b18b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7eb632743fae9a844086e8de897f3d021b507a9a"
          },
          "url": "https://www.semanticscholar.org/paper/7eb632743fae9a844086e8de897f3d021b507a9a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f9682aa7433ca60310bb4a9c73f4c4942fb74632"
          },
          "url": "https://www.semanticscholar.org/paper/f9682aa7433ca60310bb4a9c73f4c4942fb74632"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3f0e0b556a04660a2333cfc768953e44ad76986e"
          },
          "url": "https://www.semanticscholar.org/paper/3f0e0b556a04660a2333cfc768953e44ad76986e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e09d44e6c16a039437bf84ba8a5883de5e8a436d"
          },
          "url": "https://www.semanticscholar.org/paper/e09d44e6c16a039437bf84ba8a5883de5e8a436d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d627f41961d42beb56081904025bd1d5f88b788b"
          },
          "url": "https://www.semanticscholar.org/paper/d627f41961d42beb56081904025bd1d5f88b788b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f6eb50e45e0d9d6f2dfb3d729f9fb8e5ee577bec"
          },
          "url": "https://www.semanticscholar.org/paper/f6eb50e45e0d9d6f2dfb3d729f9fb8e5ee577bec"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "92bf1c069747374fbc3efb55e7a916a3e2d736da"
          },
          "url": "https://www.semanticscholar.org/paper/92bf1c069747374fbc3efb55e7a916a3e2d736da"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 6
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Text-to-Speech"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Text-to-Speech",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Tr",
          "item": "https://sciencetostartup.com/paper/zesta-zero-shot-tts-augmentation-with-domain-conditioned-training-for-data-efficient-personalized-speech-synthesis"
        }
      ]
    }
  ]
}

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(38)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(38)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline