Neural Blind Source Separation And Diarization For Distant Speech Recognition

Abstract

This paper presents a neural method for distant speech recognition (DSR) that jointly separates and diarizes speech mixtures without supervision by isolated signals. A standard separation method for multi-talker DSR is a statistical multichannel method called guided source separation (GSS). While GSS does not require signal-level supervision, it relies on speaker diarization results to handle unknown numbers of active speakers. To overcome this limitation, we introduce and train a neural inference model in a weakly-supervised manner, employing the objective function of a statistical separation method. This training requires only multichannel mixtures and their temporal annotations of speaker activities. In contrast to GSS, the trained model can jointly separate and diarize speech mixtures without any auxiliary information. The experiments with the AMI corpus show that our method outperforms GSS with oracle diarization results regarding word error rates. The code is available online.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybando2024neural

Related papers

• DCF-DS: Deep Cascade Fusion Of Diarization And Separation For Speech Recognition Under Realistic Single-channel Conditions (2024)3.58
• Low-latency Speech Separation Guided Diarization For Telephone Conversations (2022)6.77
• All-neural Online Source Separation, Counting, And Diarization For Meeting Analysis (2019)13.05
• Transcribe-to-diarize: Neural Speaker Diarization For Unlimited Number Of Speakers Using End-to-end Speaker-attributed ASR (2021)11.49
• Simultaneous Speech Recognition And Speaker Diarization For Monaural Dialogue Recordings With Target-speaker Acoustic Models (2019)0.00
• Independence-based Joint Dereverberation And Separation With Neural Source Model (2021)4.52
• Directional ASR: A New Paradigm For E2E Multi-speaker Speech Recognition With Source Localization (2020)8.09
• Semi-supervised Multi-channel Speaker Diarization With Cross-channel Attention (2023)2.26