mlsanityData to 14 Oct 2026

Convoifilter: A case study of doing cocktail party speech recognition

arXiv 2308.11380 ↗First posted 22 Aug 2023cs.SD cs.CL eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

This paper presents an end-to-end model designed to improve automatic speech recognition (ASR) for a particular speaker in a crowded, noisy environment. The model utilizes a single-channel speech enhancement module that isolates the speaker's voice from background noise (ConVoiFilter) and an ASR module. The model can decrease ASR's word error rate (WER) from 80% to 26.4% through this approach. Typically, these two components are adjusted independently due to variations in data requirements. However, speech enhancement can create anomalies that decrease ASR efficiency. By implementing a joint fine-tuning strategy, the model can reduce the WER from 26.4% in separate tuning to 14.5% in joint tuning. We openly share our pre-trained model to foster further research hf.co/nguyenvulebinh/voice-filter.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 22 Aug 2023.

Builds on

18 of 25 references.

References · 18

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  4. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  5. 2017Generalized End-to-End Loss for Speaker Verificationcited by 293
  6. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 260
  7. 2019WHAM!: Extending Speech Separation to Noisy Environmentscited by 156
  8. 2017TasNet: time-domain audio separation network for real-time, single-channel speech separationcited by 115
  9. 2018The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselinescited by 92
  10. 2020Continuous speech separation: dataset and analysiscited by 74
  11. 2018VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Maskingcited by 73
  12. 2018Building and Evaluation of a Real Room Impulse Response Datasetcited by 43
6 more
  1. 2020VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognitioncited by 32
  2. 2020Far-Field Automatic Speech Recognitioncited by 32
  3. 2020Super-Human Performance in Online Low-latency Recognition of Conversational Speechcited by 20
  4. 2018Deep Extractor Network for Target Speaker Recovery From Single Channel Speech Mixturescited by 8
  5. 2020A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verificationcited by 8
  6. 2019An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcriptioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Modelscited by 4
  2. 2026Mask2Flow-TSE: Two-Stage Target Speaker Extraction with Masking and Flow Matchingcited by 0