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

• URL: http://arxiv.org/abs/2602.07036v1
• Date: Tue, 03 Feb 2026 10:22:27 GMT
• Title: MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs
• Authors: Zien Sheikh Ali, Hunzalah Hassan Bhatti, Rabindra Nath Nandi, Shammur Absar Chowdhury, Firoj Alam,
• Abstract summary: We introduce MENASpeechBank, a reference speech bank comprising about 18K high-quality utterances from 124 speakers spanning multiple MENA countries.<n>We build a controllable synthetic data pipeline that: (i) constructs persona profiles enriched with World Values Survey-inspired attributes, (ii) defines a taxonomy of about 5K conversational scenarios, (iii) matches personas to scenarios via semantic similarity, and (iv) generates about 417K role-play conversations.
• Score: 13.58291341556655
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Audio large language models (AudioLLMs) enable instruction-following over speech and general audio, but progress is increasingly limited by the lack of diverse, conversational, instruction-aligned speech-text data. This bottleneck is especially acute for persona-grounded interactions and dialectal coverage, where collecting and releasing real multi-speaker recordings is costly and slow. We introduce MENASpeechBank, a reference speech bank comprising about 18K high-quality utterances from 124 speakers spanning multiple MENA countries, covering English, Modern Standard Arabic (MSA), and regional Arabic varieties. Building on this resource, we develop a controllable synthetic data pipeline that: (i) constructs persona profiles enriched with World Values Survey-inspired attributes, (ii) defines a taxonomy of about 5K conversational scenarios, (iii) matches personas to scenarios via semantic similarity, (iv) generates about 417K role-play conversations with an LLM where the user speaks as the persona and the assistant behaves as a helpful agent, and (v) synthesizes the user turns by conditioning on reference speaker audio to preserve speaker identity and diversity. We evaluate both synthetic and human-recorded conversations and provide detailed analysis. We will release MENASpeechBank and the generated conversations publicly for the community.

Related papers

• VoiceAgentBench: Are Voice Assistants ready for agentic tasks? [5.639970295197759]
  We introduce VoiceAgentBench, a benchmark to evaluate SpeechLMs in realistic spoken agentic settings.<n>It comprises over 5,500 synthetic spoken queries grounded in Indian context.<n>It measures tool selection accuracy, structural consistency, and the correctness of tool invocations, including adversarial robustness.
  arXiv  Detail & Related papers  (2025-10-09T09:11:38Z)
• Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech [10.576716279533404]
  We propose a human-like agent that generates speech responses based on conversation mood and responsive style information.<n>We build a novel MultiSensory Conversation dataset focused on speech to enable agents to generate natural speech.<n> Experimental results demonstrate the effectiveness of utilizing both visual and audio modalities in conversation to generate engaging speech.
  arXiv  Detail & Related papers  (2025-09-18T05:14:10Z)
• What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study [58.55905182336196]
  Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation.<n>We investigate the role of speech tokenizer designs in LLM-centric SLMs, augmented by speech heads and speaker modeling.<n>We introduce multi-token prediction (MTP) into SLMs, enabling each hidden state to decode multiple speech tokens.
  arXiv  Detail & Related papers  (2025-06-14T15:26:31Z)
• Multimodal Conversation Structure Understanding [12.29827265137757]
  Large language models' ability to understand fine-grained conversational structure remains underexplored.<n>We present a human annotated dataset of 4,398 annotations for speakers and reply-to relationship, 5,755 addressees, and 3,142 side-participants.<n>We evaluate popular audio-visual LLMs and vision-language models on our dataset, and our experimental results suggest that multimodal conversational structure understanding remains challenging.
  arXiv  Detail & Related papers  (2025-05-23T06:41:54Z)
• Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models [58.43486430996411]
  Large Audio-Language Models (LALMs) have recently unlocked audio dialogue capabilities, enabling direct spoken exchanges with humans.<n>We propose an Audio Dialogue Understanding Benchmark (ADU-Bench) to evaluate the performance of LALMs in the open-ended audio dialogue understanding.<n>ADU-Bench includes over 20,000 open-ended audio dialogues for the assessment of LALMs.
  arXiv  Detail & Related papers  (2024-12-06T16:34:15Z)
• IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities [55.11130688075417]
  We introduce IntrinsicVoic,e an LLM designed with intrinsic real-time voice interaction capabilities. Our novelty architecture, GroupFormer, can reduce speech sequences to lengths comparable to text sequences. We construct a multi-turn speech-to-speech dialogue dataset named method-500k which includes nearly 500k turns of speech-to-speech dialogues.
  arXiv  Detail & Related papers  (2024-10-09T05:04:31Z)
• ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech [58.93395189153713]
  We extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes. Our model shows great improvements over speaker-embedding-based multi-speaker TTS methods.
  arXiv  Detail & Related papers  (2022-11-07T13:35:16Z)
• End-to-end Spoken Conversational Question Answering: Task, Dataset and Model [92.18621726802726]
  In spoken question answering, the systems are designed to answer questions from contiguous text spans within the related speech transcripts. We propose a new Spoken Conversational Question Answering task (SCQA), aiming at enabling the systems to model complex dialogue flows. Our main objective is to build the system to deal with conversational questions based on the audio recordings, and to explore the plausibility of providing more cues from different modalities with systems in information gathering.
  arXiv  Detail & Related papers  (2022-04-29T17:56:59Z)
• Spoken Style Learning with Multi-modal Hierarchical Context Encoding for Conversational Text-to-Speech Synthesis [59.27994987902646]
  The study about learning spoken styles from historical conversations is still in its infancy. Only the transcripts of the historical conversations are considered, which neglects the spoken styles in historical speeches. We propose a spoken style learning approach with multi-modal hierarchical context encoding.
  arXiv  Detail & Related papers  (2021-06-11T08:33:52Z)
• Few Shot Adaptive Normalization Driven Multi-Speaker Speech Synthesis [18.812696623555855]
  We present a novel few shot multi-speaker speech synthesis approach (FSM-SS) Given an input text and a reference speech sample of an unseen person, FSM-SS can generate speech in that person's style in a few shot manner. We demonstrate how the affine parameters of normalization help in capturing the prosodic features such as energy and fundamental frequency.
  arXiv  Detail & Related papers  (2020-12-14T04:37:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.