# Conditioned in Training, Dispensable at Inference: Typological Conditioning for Multilingual Speech Translation

arXiv: https://arxiv.org/abs/2605.16026 · HTML: https://mlsanity.com/paper/2605.16026/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 15 May 2026.

## Builds on (most cited first, 30 of 36)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [Textless Speech-to-Speech Translation on Real Data](https://mlsanity.com/paper/2112.08352/) (2021)
- [Direct speech-to-speech translation with a sequence-to-sequence model](https://mlsanity.com/paper/1904.06037/) (2019)
- [IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2506.21619/) (2025)
- [Translatotron 2: High-quality direct speech-to-speech translation with voice preservation](https://mlsanity.com/paper/2107.08661/) (2021)
- [CVSS Corpus and Massively Multilingual Speech-to-Speech Translation](https://mlsanity.com/paper/2201.03713/) (2022)
- [Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing](https://mlsanity.com/paper/1807.00914/) (2018)
- [UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units](https://mlsanity.com/paper/2212.08055/) (2022)
- [Adaptive Machine Translation with Large Language Models](https://mlsanity.com/paper/2301.13294/) (2023)
- [VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning](https://mlsanity.com/paper/2509.24650/) (2025)
- [FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot](https://mlsanity.com/paper/2509.02020/) (2025)
- [ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching](https://mlsanity.com/paper/2506.13053/) (2025)
- [Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations](https://mlsanity.com/paper/2004.14923/) (2020)
- [High-Fidelity Simultaneous Speech-To-Speech Translation](https://mlsanity.com/paper/2502.03382/) (2025)
- [StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching](https://mlsanity.com/paper/2412.04724/) (2024)
- [HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanism](https://mlsanity.com/paper/2303.08636/) (2023)

## Abstract (arXiv)

Multilingual speech translation frontends built on speech large language models typically condition on language identity, as a learned embedding or a prompted language name. Such a signal, however, is learned separately for each language and transfers nothing between typologically related languages. In this paper, we present TypoCast, a frontend that conditions on the typological profile of the source language rather than on its label alone. A typology-informed hierarchical language encoding represents each language by its morphological type, constituent order and family, so that supervision is shared among related languages. A dual-route mixture-of-experts adapter routes inputs through a shared typological route together with a per-language residual, and a typology-aware prompt conveys the same profile to the decoder. Extensive experiments on CVSS-C demonstrate that TypoCast surpasses state-of-the-art speech-to-speech translation systems on French, German and Spanish to English, averaged over the three directions, and outperforms the identity-conditioned S2ST-Omni on every language of a seven-language inventory, with only 228M trainable parameters. Ablation studies further reveal that the conditioning signal acts during training and is dispensable at inference: a model trained without it is consistently worse, whereas removing it from a trained model changes BLEU by less than 0.2, and expert usage is consistent with the signal shaping how adapter capacity is divided among languages.