# Xiaomi-CocktailASR-1 Technical Report

arXiv: https://arxiv.org/abs/2609.11274 · HTML: https://mlsanity.com/paper/2609.11274/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language](https://mlsanity.com/paper/2212.07525/) (2022)
- [CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking](https://mlsanity.com/paper/2303.00332/) (2023)
- [Serialized Output Training for End-to-End Overlapped Speech Recognition](https://mlsanity.com/paper/2003.12687/) (2020)
- [End-to-End Speaker-Attributed ASR with Transformer](https://mlsanity.com/paper/2104.02128/) (2021)
- [Adapting self-supervised models to multi-talker speech recognition using speaker embeddings](https://mlsanity.com/paper/2211.00482/) (2022)
- [Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions](https://mlsanity.com/paper/2409.08596/) (2024)
- [Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition](https://mlsanity.com/paper/1906.10876/) (2019)
- [Extending Whisper with prompt tuning to target-speaker ASR](https://mlsanity.com/paper/2312.08079/) (2023)
- [Summary On The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge](https://mlsanity.com/paper/2202.03647/) (2022)
- [Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System](https://mlsanity.com/paper/2407.09817/) (2024)
- [Conformer-based Target-Speaker Automatic Speech Recognition for Single-Channel Audio](https://mlsanity.com/paper/2308.05218/) (2023)
- [Advancing Multi-talker ASR Performance with Large Language Models](https://mlsanity.com/paper/2408.17431/) (2024)
- [Alignment-Free Training for Transducer-based Multi-Talker ASR](https://mlsanity.com/paper/2409.20301/) (2024)
- [SQ-Whisper: Speaker-Querying based Whisper Model for Target-Speaker ASR](https://mlsanity.com/paper/2412.05589/) (2024)
- [Thinking in cocktail party: Chain-of-Thought and reinforcement learning for target speaker automatic speech recognition](https://mlsanity.com/paper/2509.15612/) (2025)

## Built on by (most cited first, 1 of 1)

- [Asymmetric Classifier-Free Guidance for Target-Speaker ASR](https://mlsanity.com/paper/2609.30476/) (2026)

## Abstract (arXiv)

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.