# Unifying Speech Recognition, Synthesis and Conversion with Autoregressive Transformers

arXiv: https://arxiv.org/abs/2601.10770 · HTML: https://mlsanity.com/paper/2601.10770/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 46 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 30 of 32)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [Speech Resynthesis from Discrete Disentangled Self-Supervised Representations](https://mlsanity.com/paper/2104.00355/) (2021)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision](https://mlsanity.com/paper/2302.03540/) (2023)
- [On decoder-only architecture for speech-to-text and large language model integration](https://mlsanity.com/paper/2307.03917/) (2023)
- [Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens](https://mlsanity.com/paper/2503.01710/) (2025)
- [IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2506.21619/) (2025)
- [Unsupervised Speech Decomposition via Triple Information Bottleneck](https://mlsanity.com/paper/2004.11284/) (2020)
- [SLM: Bridge the thin gap between speech and text foundation models](https://mlsanity.com/paper/2310.00230/) (2023)
- [ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering](https://mlsanity.com/paper/2401.07333/) (2024)
- [LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models](https://mlsanity.com/paper/2310.02943/) (2023)
- [Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition](https://mlsanity.com/paper/2306.16007/) (2023)
- [MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder](https://mlsanity.com/paper/2505.07916/) (2025)
- [FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration](https://mlsanity.com/paper/2501.14350/) (2025)
- [VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning](https://mlsanity.com/paper/2509.24650/) (2025)
- [Emotion Intensity and its Control for Emotional Voice Conversion](https://mlsanity.com/paper/2201.03967/) (2022)
- [IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System](https://mlsanity.com/paper/2502.05512/) (2025)
- [Voice-preserving Zero-shot Multiple Accent Conversion](https://mlsanity.com/paper/2211.13282/) (2022)
- [Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNet](https://mlsanity.com/paper/1903.12389/) (2019)

## Built on by (most cited first, 2 of 2)

- [Multimodal Co-Generation With Continuous Bitstream Diffusion](https://mlsanity.com/paper/2610.14349/) (2026)
- [Training a Compact, Strong, and Realistic Text-to-Speech Model](https://mlsanity.com/paper/2610.14776/) (2026)

## Abstract (arXiv)

Traditional speech systems typically rely on separate, task-specific models for text-to-speech (TTS), automatic speech recognition (ASR), and voice conversion (VC), resulting in fragmented pipelines that limit scalability, efficiency, and cross-task generalization. In this paper, we present General-Purpose Audio (GPA), a unified audio foundation model that integrates multiple core speech tasks within a single large language model (LLM) architecture. GPA operates on a shared discrete audio token space and supports instruction-driven task induction, enabling a single autoregressive model to flexibly perform TTS, ASR, and VC without architectural modifications. This unified design combines a fully autoregressive formulation over discrete speech tokens, joint multi-task training across speech domains, and a scalable inference pipeline that achieves high concurrency and throughput. The resulting model family supports efficient multi-scale deployment, including a lightweight 0.3B-parameter variant optimized for edge and resource-constrained environments. Together, these design choices demonstrate that a unified autoregressive architecture can achieve competitive performance across diverse speech tasks while remaining viable for low-latency, practical deployment.