Exploring The Time-domain Deep Attractor Network With Two-stream Architectures In A Reverberant Environment
2020 · Hangting Chen, Pengyuan Zhang
Abstract
Deep attractor networks (DANs) perform speech separation with discriminative embeddings and speaker attractors. Compared with methods based on the permutation invariant training (PIT), DANs define a deep embedding space and deliver a more elaborate representation on each time-frequency (T-F) bin. However, it has been observed that the DANs achieve limited improvement on the signal quality if directly deployed in a reverberant environment. Following the success of time-domain separation networks on the clean mixture speech, we propose a time-domain DAN (TD-DAN) with two-streams of convolutional networks, which efficiently perform both dereverberation and separation tasks under the condition of a variable number of speakers. The speaker encoding stream (SES) of the TD-DAN is trained to model the speaker information in the embedding space. The speech decoding stream (SDS) accepts speaker attractors from the SES and learns to estimate early reflections from the spectro-temporal representat
Authors
(none)
Tags
Stats
Related papers
- Speaker-independent Speech Separation With Deep Attractor Network (2017)16.84
- Deep Attractor Network For Single-microphone Speaker Separation (2016)17.88
- Cracking The Cocktail Party Problem By Multi-beam Deep Attractor Network (2018)9.92
- On Time Domain Conformer Models For Monaural Speech Separation In Noisy Reverberant Acoustic Environments (2023)5.84
- Dualstream Contextual Fusion Network: Efficient Target Speaker Extraction By Leveraging Mixture And Enrollment Interactions (2025)0.00
- Deft-an: Dense Frequency-time Attentive Network For Multichannel Speech Enhancement (2022)12.10
- Deformable Temporal Convolutional Networks For Monaural Noisy Reverberant Speech Separation (2022)8.09
- Dasformer: Deep Alternating Spectrogram Transformer For Multi/single-channel Speech Separation (2023)0.00