# Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech

arXiv: https://arxiv.org/abs/1905.03500 · HTML: https://mlsanity.com/paper/1905.03500/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2019.

## Built on by (most cited first, 8 of 8)

- [Multi-turn RNN-T for streaming recognition of multi-party speech](https://mlsanity.com/paper/2112.10200/) (2021)
- [Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speech](https://mlsanity.com/paper/2112.05863/) (2021)
- [Mixture Encoder for Joint Speech Separation and Recognition](https://mlsanity.com/paper/2306.12173/) (2023)
- [A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References](https://mlsanity.com/paper/2508.14623/) (2025)
- [Disentangling the Impacts of Language and Channel Variability on Speech Separation Networks](https://mlsanity.com/paper/2203.16040/) (2022)
- [Separator-Transducer-Segmenter: Streaming Recognition and Segmentation of Multi-party Speech](https://mlsanity.com/paper/2205.05199/) (2022)
- [Compositional Clustering: Applications to Multi-Label Object Recognition and Speaker Identification](https://mlsanity.com/paper/2109.04160/) (2021)
- [A Survey on Spoken Italian Datasets and Corpora](https://mlsanity.com/paper/2501.06557/) (2025)

## Abstract (arXiv)

Significant performance degradation of automatic speech recognition (ASR) systems is observed when the audio signal contains cross-talk. One of the recently proposed approaches to solve the problem of multi-speaker ASR is the deep clustering (DPCL) approach. Combining DPCL with a state-of-the-art hybrid acoustic model, we obtain a word error rate (WER) of 16.5 % on the commonly used wsj0-2mix dataset, which is the best performance reported thus far to the best of our knowledge. The wsj0-2mix dataset contains simulated cross-talk where the speech of multiple speakers overlaps for almost the entire utterance. In a more realistic ASR scenario the audio signal contains significant portions of single-speaker speech and only part of the signal contains speech of multiple competing speakers. This paper investigates obstacles of applying DPCL as a preprocessing method for ASR in such a scenario of sparsely overlapping speech. To this end we present a data simulation approach, closely related to the wsj0-2mix dataset, generating sparsely overlapping speech datasets of arbitrary overlap ratio. The analysis of applying DPCL to sparsely overlapping speech is an important interim step between the fully overlapping datasets like wsj0-2mix and more realistic ASR datasets, such as CHiME-5 or AMI.