# Improved Speaker-Dependent Separation for CHiME-5 Challenge

## TL;DR

This paper presents an improved speaker-dependent speech separation system for the CHiME-5 challenge, achieving significant WER reduction through speaker-aware training, data processing, and beamforming techniques in complex conversational scenarios.

## Contribution

It introduces a unified speaker-aware separation model using i-vectors and advanced data processing, leading to notable WER improvements over previous systems.

## Key findings

- 10% absolute WER reduction on development set
- Achieved WER of 60.15% surpassing previous challenge results
- Single model effectively handles multiple speakers in overlapped speech

## Abstract

This paper summarizes several follow-up contributions for improving our submitted NWPU speaker-dependent system for CHiME-5 challenge, which aims to solve the problem of multi-channel, highly-overlapped conversational speech recognition in a dinner party scenario with reverberations and non-stationary noises. We adopt a speaker-aware training method by using i-vector as the target speaker information for multi-talker speech separation. With only one unified separation model for all speakers, we achieve a 10\% absolute improvement in terms of word error rate (WER) over the previous baseline of 80.28\% on the development set by leveraging our newly proposed data processing techniques and beamforming approach. With our improved back-end acoustic model, we further reduce WER to 60.15\% which surpasses the result of our submitted CHiME-5 challenge system without applying any fusion techniques.