arXiv AI September 21, 2026 By Zien Sheikh Ali, Hunzalah Hassan Bhatti, Rabindra Nath Nandi, Shammur Absar Chowdhury, Firoj Alam

MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs

Read the original on arXiv AI →

MENASpeechBank is a new reference voice bank that provides about 18,000 high‑quality utterances from 124 speakers across multiple MENA countries, covering English, Modern Standard Arabic, and regional Arabic varieties. The dataset is built through a controllable pipeline that creates persona profiles inspired by the World Values Survey, defines a taxonomy of roughly 5,000 conversational scenarios, matches personas to scenarios via semantic similarity, and generates around 417,000 role‑play conversations using an LLM. Synthetic speaker‑conditioned user‑turn audio is produced from reference recordings to maintain speaker diversity, and both synthetic and human‑recorded conversations are evaluated and analyzed for quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 3

Efficient ASR Training with Conversations that Never Happened

arXiv:2606. 03957v1 Announce Type: cross Abstract: Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data.

By M\'at\'e Gedeon, P\'eter Mihajlik

llms multimodal benchmarks

Hugging Face Trending Papers

Aug 12

Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder

Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time.

llms multimodal benchmarks

arXiv Computation and Language

Sep 2

SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue

arXiv:2603.16783v2 Announce Type: replace Abstract: Robust voice agents require exposure to the full diversity of how people interact through speech. However, obtaining enough spoken interactions is...

By Jonggeun Lee, Junseong Pyo, Jeongmin Park, Yohan Jo

agents

Hugging Face Trending Papers

Jun 2

Efficient ASR Training with Conversations that Never Happened

Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data. We propose an augmentation pipeline that generates scenario-level dialogues with participant metadata, maps speaker attributes to TTS voice profiles, and assembles synthesized utterances into speaker-aware simulated conversations.

llms multimodal benchmarks

arXiv Computation and Language

Sep 11

Nuha-Speech: Building General-Purpose Arabic Speech-LLMs

Nuha‑Speech is a new initiative aimed at creating general‑purpose Arabic speech‑large language models (speech‑LLMs). It includes the construction of a large Arabic Speech Question‑Answering corpus with over 1.5 million samples for instruction tuning, supervised fine‑tuning of Qwen‑Omni model variants at various scales, and a systematic evaluation framework with diverse tasks and tailored metrics. The project seeks to establish foundational infrastructure for Arabic speech‑LLMs amid limited Arabic speech resources.

By Yingzhi Wang, Reem Alhazzani, Muhammad Alqurishi

llms fine-tuning

arXiv AI

Jun 18

Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors

arXiv:2606. 19325v1 Announce Type: cross Abstract: Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings.

By Michael Finkelson, Daniel Segal, Eitan Richardson, Shahar Armon, Nani Goldring, Poriya Panet, Nir Zabari, Benjamin Brazowski, Or Patashnik, Yoav HaCohen

rag benchmarks

One email a morning, machine-written

Related stories

Efficient ASR Training with Conversations that Never Happened

Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder

SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue

Efficient ASR Training with Conversations that Never Happened

Nuha-Speech: Building General-Purpose Arabic Speech-LLMs

Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors