PulseAugur
EN
LIVE 17:33:37

New benchmark PashtoTTS-Bench evaluates low-resource text-to-speech systems

By PulseAugur Editorial · [2 sources] ·

A new benchmark, PashtoTTS-Bench, has been developed to evaluate text-to-speech systems for low-resource languages like Pashto, addressing limitations of traditional round-trip ASR methods. The benchmark introduces the INSV framework, which assesses intelligibility, naturalness, script fidelity, and verification. The initial run in April-May 2026 evaluated several TTS systems, with OmniVoice auto achieving the lowest word error rate (WER) under the omniASR_CTC_300M_v2 system. AI

IMPACT Introduces a new evaluation framework for low-resource TTS, potentially improving quality assessment for underserved languages.

RANK_REASON The cluster describes a new academic paper introducing a benchmark for evaluating text-to-speech systems.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New benchmark PashtoTTS-Bench evaluates low-resource text-to-speech systems

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · Hanif Rahman ·

    PashtoTTS-Bench: automated screening for low-resource non-Latin-script text-to-speech

    arXiv:2605.26978v1 Announce Type: new Abstract: Text-to-speech (TTS) evaluation for low-resource non-Latin-script languages can fail when it relies on a single ASR round-trip word error rate (WER). A system may produce no audio, speak a neighbouring language, preserve target scri…

  2. arXiv cs.CL TIER_1 English(EN) · Hanif Rahman ·

    PashtoTTS-Bench: automated screening for low-resource non-Latin-script text-to-speech

    Text-to-speech (TTS) evaluation for low-resource non-Latin-script languages can fail when it relies on a single ASR round-trip word error rate (WER). A system may produce no audio, speak a neighbouring language, preserve target script text only in an ASR transcript, or sound unna…

RELATED TOPICS