mlsanityData to 7 Oct 2026

Personalized Keyphrase Detection using Speaker and Environment Information

arXiv 2104.13970 ↗First posted 28 Apr 2021eess.AS cs.LG cs.SDcited by 8

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce a streaming keyphrase detection system that can be easily customized to accurately detect any phrase composed of words from a large vocabulary. The system is implemented with an end-to-end trained automatic speech recognition (ASR) model and a text-independent speaker verification model. To address the challenge of detecting these keyphrases under various noisy conditions, a speaker separation model is added to the feature frontend of the speaker verification model, and an adaptive noise cancellation (ANC) algorithm is included to exploit cross-microphone noise coherence. Our experiments show that the text-independent speaker verification model largely reduces the false triggering rate of the keyphrase detection, while the speaker separation model and adaptive noise cancellation largely reduce false rejections.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 22 of its 40 references that are in the map. First posted on arXiv 28 Apr 2021.

Builds on

22 of 40 references.

References · 22

  1. 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
  2. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  3. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  4. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 596
  5. 2015LSTM: A Search Space Odysseycited by 315
  6. 2017Generalized End-to-End Loss for Speaker Verificationcited by 290
  7. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 230
  8. 2015Deep clustering: Discriminative embeddings for segmentation and separationcited by 211
  9. 2020A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latencycited by 99
  10. 2017Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networkscited by 97
  11. 2019Recognizing long-form speech using streaming end-to-end modelscited by 77
  12. 2018VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Maskingcited by 72
10 more
  1. 2019CN-CELEB: a challenging Chinese speaker recognition datasetcited by 47
  2. 2020Voice Separation with an Unknown Number of Multiple Speakerscited by 46
  3. 2019Optimizing Speech Recognition For The Edgecited by 32
  4. 2020VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognitioncited by 29
  5. 2018End-to-End Streaming Keyword Spottingcited by 25
  6. 2017Streaming Small-Footprint Keyword Spotting using Sequence-to-Sequence Modelscited by 19
  7. 2018Attention-based End-to-End Models for Small-Footprint Keyword Spottingcited by 18
  8. 2021Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognitioncited by 10
  9. 2020Version Control of Speaker Recognition Systemscited by 6
  10. 2015Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Networkcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 2; 2023: 1; 2024: 0; 2025: 1; 2026: 1.

8 papers.

  1. 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
  2. 2021Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detectioncited by 31
  3. 2023E3 TTS: Easy End-to-End Diffusion-based Text to Speechcited by 30
  4. 2021Multi-user VoiceFilter-Lite via Attentive Speaker Embeddingcited by 4
  5. 2022Closing the Gap between Single-User and Multi-User VoiceFilter-Litecited by 1
  6. 2022Improving Voice Trigger Detection with Metric Learningcited by 1
  7. 2025Keyword Spotting with Hyper-Matched Filters for Small Footprint Devicescited by 0
  8. 2026Training Intelligent Voice Assistant Wakeup with Controllable Synthetic Conversationscited by 0