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.
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.
arXiv:2609.10394v1 Announce Type: cross Abstract: Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the...
arXiv:2607. 08111v1 Announce Type: cross Abstract: Training target speaker extraction (TSE) models for real conversational mixtures remains challenging because large-scale training corpora and clean target speech for supervision are unavailable.
The paper introduces a method called randomized intermediate guidance for training tandem speech-to-speech models, where a large language model (LLM) acts as a backend providing candidate responses while the user is speaking. Instead of simulating the backend’s guidance, the approach derives guidance directly from the conversation corpus, using target responses for informative guidance and randomly sampled responses to simulate irrelevant updates. Experiments on synthetic dialogues and 3.8k hours of real conversations show that this technique yields response quality comparable to LLM-generated baselines while improving natural turn‑taking and audio‑judge naturalness.
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.
arXiv:2607. 08371v1 Announce Type: cross Abstract: Synthetic multi-speaker conversations are widely used to train conversational automatic speech recognition (ASR) systems, but it remains unclear which timing properties make simulated data most useful.
arXiv:2609.22697v1 Announce Type: new Abstract: Recently, text-to-speech systems have made significant progress in speech expressiveness and controllability. However, the speaking style of generated...
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.
TalkFa introduces a unified benchmark for Farsi dialogue generation and understanding, comprising three datasets: WIKI‑FADIAL (4.2K Wikipedia‑grounded dialogues), DAILYDIALOG‑FA (6.6K dialogues with dialogue‑act and emotion annotations), and PLAYDIAL‑FA (2.1K theatrical dialogues with sentiment labels). All dialogues are curated through multi‑stage review by native speakers, ensuring high quality. Experiments show that LoRA fine‑tuning improves generation performance with less data, while specific models excel on classification tasks, and human evaluation confirms the benchmark’s reliability.
The paper introduces a phoneme-guided text-to-speech (TTS) augmentation pipeline for automatic speech recognition (ASR) that links multilingual speech generation with candidate-text selection and reference-speech quality control. It proposes phoneme-frequency-guided selection (PFGS), which prioritizes candidate texts containing common phonetic content based on real ASR training transcripts. Experiments across four languages and 13 test sets show that random text selection improves recognition on 11 test sets, while PFGS further improves nine test sets with relative word error rate reductions up to 19.3%, and reference-speech filtering also contributes to performance gains.
arXiv:2609.22214v1 Announce Type: new Abstract: Long multilingual conversational spoken question answering requires systems to balance long-range transcript semantics with sparse acoustic and speaker...
Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings. These systems operate within speech-only pipelines that produce clean vocal sequences without the ambient texture of real conversations.