Analysis Of Deep Clustering As Preprocessing For Automatic Speech Recognition Of Sparsely Overlapping Speech

Abstract

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 t

Stats

• citations18
• S2 citations—
• github stars0
• HF likes0
• heat score9.59
• arxiv keymenne2019analysis

Related papers

• Single-channel Multi-speaker Separation Using Deep Clustering (2016)0.00
• Multi-channel Speech Separation Using Deep Embedding Model With Multilayer Bootstrap Networks (2019)0.00
• Low-latency Deep Clustering For Speech Separation (2019)8.09
• Elevating Robust Multi-talker ASR By Decoupling Speaker Separation And Speech Recognition (2025)0.00
• Assessing The Robustness Of Spectral Clustering For Deep Speaker Diarization (2024)3.58
• Enhancements For Audio-only Diarization Systems (2019)0.00
• Highly Efficient Real-time Streaming And Fully On-device Speaker Diarization With Multi-stage Clustering (2022)0.00
• Directed Speech Separation For Automatic Speech Recognition Of Long Form Conversational Speech (2021)2.26