# Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals

arXiv: https://arxiv.org/abs/2006.14150 · HTML: https://mlsanity.com/paper/2006.14150/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

## Built on by (most cited first, 5 of 5)

- [Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors](https://mlsanity.com/paper/2206.02432/) (2022)
- [BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR](https://mlsanity.com/paper/2305.13716/) (2023)
- [On Robustness to Missing Video for Audiovisual Speech Recognition](https://mlsanity.com/paper/2312.10088/) (2023)
- [Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR](https://mlsanity.com/paper/2203.00232/) (2022)
- [SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition](https://mlsanity.com/paper/2506.12672/) (2025)

## Abstract (arXiv)

Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as extracting multiple sequential sources from a mixture sequence. We extend the standard sequence-to-sequence model to a conditional multi-sequence model, which explicitly models the relevance between multiple output sequences with the probabilistic chain rule. Based on this extension, our model can conditionally infer output sequences one-by-one by making use of both input and previously-estimated contextual output sequences. This model additionally has a simple and efficient stop criterion for the end of the transduction, making it able to infer the variable number of output sequences. We take speech data as a primary test field to evaluate our methods since the observed speech data is often composed of multiple sources due to the nature of the superposition principle of sound waves. Experiments on several different tasks including speech separation and multi-speaker speech recognition show that our conditional multi-sequence models lead to consistent improvements over the conventional non-conditional models.