Cover Image

The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Menta, Venkata Pushpak Teja
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost
by: Menta, Venkata Pushpak Teja
Published: (2026)

PSP: An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speech
by: Menta, Venkata Pushpak Teja
Published: (2026)

LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity Preservation
by: Menta, Venkata Pushpak Teja
Published: (2026)

Mind the Gap: Entity-Preserved Context-Aware ASR Structured Transcriptions
by: Altinok, Duygu
Published: (2025)

Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation
by: Ghosh, Sreyan, et al.
Published: (2024)

Few-Shot Contrastive Adaptation for Audio Abuse Detection in Low-Resource Indic Languages
by: Sankaran, Aditya Narayan, et al.
Published: (2026)

Reverb: Open-Source ASR and Diarization from Rev
by: Bhandari, Nishchal, et al.
Published: (2024)

IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
by: Sankar, Ashwin, et al.
Published: (2024)

Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets
by: Geng, Xuelong, et al.
Published: (2024)

Performant ASR Models for Medical Entities in Accented Speech
by: Afonja, Tejumade, et al.
Published: (2024)

Revealing the Role of Audio Channels in ASR Performance Degradation
by: Huang, Kuan-Tang, et al.
Published: (2025)

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM
by: Yu, Jiawei, et al.
Published: (2024)

The THUEE System Description for the IARPA OpenASR21 Challenge
by: Zhao, Jing, et al.
Published: (2022)

A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data
by: Chou, Cheng-Kang, et al.
Published: (2025)

Synthetic Speech Source Tracing using Metric Learning
by: Koutsianos, Dimitrios, et al.
Published: (2025)

CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonese
by: Chen, Dazhong, et al.
Published: (2025)

The State Of TTS: A Case Study with Human Fooling Rates
by: Varadhan, Praveen Srinivasa, et al.
Published: (2025)

PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation
by: He, Jiajun, et al.
Published: (2025)

EE-TTS: Emphatic Expressive TTS with Linguistic Information
by: Zhong, Yi, et al.
Published: (2023)

Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
by: Tian, Jinchuan, et al.
Published: (2026)

MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Model
by: Huang, Hsiao-Ying, et al.
Published: (2025)

MOSS-TTS Technical Report
by: Gong, Yitian, et al.
Published: (2026)

MunTTS: A Text-to-Speech System for Mundari
by: Gumma, Varun, et al.
Published: (2024)

Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptation
by: He, Jiaxu, et al.
Published: (2026)

SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing
by: Ma, Ziyang, et al.
Published: (2026)

AutoMode-ASR: Learning to Select ASR Systems for Better Quality and Cost
by: Gündüz, Ahmet, et al.
Published: (2024)

TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch
by: Song, Xingchen, et al.
Published: (2024)

RephraseTTS: Dynamic Length Text based Speech Insertion with Speaker Style Transfer
by: Matiyali, Neeraj, et al.
Published: (2025)

MLMA: Towards Multilingual ASR With Mamba-based Architectures
by: Ali, Mohamed Nabih, et al.
Published: (2025)

Bridging Language Gaps in Audio-Text Retrieval
by: Yan, Zhiyong, et al.
Published: (2024)

PashtoTTS-Bench: automated screening for low-resource non-Latin-script text-to-speech
by: Rahman, Hanif
Published: (2026)

Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation
by: Yang, Tianle, et al.
Published: (2026)

GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
by: Chen, Guoguo, et al.
Published: (2021)

DARS: Dysarthria-Aware Rhythm-Style Synthesis for ASR Enhancement
by: Wu, Minghui, et al.
Published: (2026)

Arabic Little STT: Arabic Children Speech Recognition Dataset
by: Alkadri, Mouhand, et al.
Published: (2025)

Elderly-Contextual Data Augmentation via Speech Synthesis for Elderly ASR
by: Lee, Minsik, et al.
Published: (2026)

PromptASR for contextualized ASR with controllable style
by: Yang, Xiaoyu, et al.
Published: (2023)

A Non-autoregressive Model for Joint STT and TTS
by: Sunder, Vishal, et al.
Published: (2025)

A Calculus-Based Framework for Determining Vocabulary Size in End-to-End ASR
by: Kopparapu, Sunil Kumar
Published: (2026)

LOTUSDIS: A Thai far-field meeting corpus for robust conversational ASR
by: Tipaksorn, Pattara, et al.
Published: (2025)