mlsanityData to 19 Oct 2026

Towards noise-robust speech inversion through multi-task learning with speech enhancement

arXiv 2601.14516 ↗First posted 20 Jan 2026eess.AS cs.SDcited by 0

On the map: Speech and audio language models → Speech enhancement and noise suppression

Abstract (arXiv)

Recent studies demonstrate the effectiveness of Self Supervised Learning (SSL) speech representations for Speech Inversion (SI). However, applying SI in real-world scenarios remains challenging due to the pervasive presence of background noise. We propose a unified framework that integrates Speech Enhancement (SE) and SI models through shared SSL-based speech representations. In this framework, the SSL model is trained not only to support the SE module in suppressing noise but also to produce representations that are more informative for the SI task, allowing both modules to benefit from joint training. At a Signal-to-Noise Ratio of -5 db, our method for the SI task achieves relative improvements over the baseline of 80.95% under babble noise and 38.98% under non-babble noise, as measured by the average Pearson product-moment correlation across all estimated parameters.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models. Builds on 11 of its 24 references that are in the map. First posted on arXiv 20 Jan 2026.

Builds on

11 of 24 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Exploiting Consistency-Preserving Loss and Perceptual Contrast Stretching to Boost SSL-based Speech Enhancement8 Aug
  2. 2022Investigating self-supervised learning for speech enhancement and separation15 Mar

Other references · 9

  1. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 2,135
  2. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 694
  3. 2019Phase-aware Speech Enhancement with Deep Complex U-Netcited by 110
  4. 2021Interspeech 2021 Deep Noise Suppression Challengecited by 96
  5. 2022Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speechcited by 34
  6. 2023Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variablescited by 8
  7. 2022Audio Data Augmentation for Acoustic-to-articulatory Speech Inversion using Bidirectional Gated RNNscited by 5
  8. 2025Enhancing Acoustic-to-Articulatory Speech Inversion by Incorporating Nasalitycited by 3
  9. 2025Acoustic to Articulatory Speech Inversion for Children with Velopharyngeal Insufficiencycited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Boosting Self-Supervised Embeddings for Speech Enhancement
  2. 2023Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss
  3. 2026Rethinking Speech Representation Aggregation in Speech Enhancement: A Phonetic Mutual Information Perspective
  4. 2026Position-invariant Fine-tuning of Speech Enhancement Models with Self-supervised Speech Representations
  5. 2022Joint Training of Speech Enhancement and Self-supervised Model for Noise-robust ASR
  6. 2025Generic Speech Enhancement with Self-Supervised Representation Space Loss
  7. 2024CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
  8. 2024A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement