Speech & Audio

Speech recognition/synthesis, audio generation, music, signal processing for audio.

A topic in the Science corpus, drawn from 1,054 papers.

Trusted voices in Speech & Audio

Ordered by the trust Speech & Audio's own network concentrates on each researcher, most first.

  1. Stéphane Mallat — trusted by 508 researchers here
  2. Andrew W. Senior — trusted by 443 researchers here
  3. Heiga Zen — trusted by 364 researchers here
  4. Abdel-rahman Mohamed — trusted by 299 researchers here
  5. Dong Yu — trusted by 284 researchers here
  6. Yu Zhang — trusted by 301 researchers here
  7. Frederick Jelinek — trusted by 213 researchers here
  8. Daniel Povey — trusted by 271 researchers here
  9. James R. Glass — trusted by 203 researchers here
  10. Hasim Sak — trusted by 250 researchers here
  11. Jae S. Lim — trusted by 232 researchers here
  12. Daniel W. Griffin — trusted by 232 researchers here

Most-cited papers in Speech & Audio

Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.

  1. Independent component analysis: algorithms and applications (2000) — 9,240 citations
  2. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations (2020, Neural Information Processing Systems) — 8,824 citations
  3. WaveNet: A Generative Model for Raw Audio (2016) — 8,319 citations
  4. Discrete Time Signal Processing (2004) — 8,269 citations
  5. Robust Speech Recognition via Large-Scale Weak Supervision (2022, International Conference on Machine Learning) — 7,824 citations
  6. The Kaldi Speech Recognition Toolkit (2011) — 6,607 citations
  7. Speaker Verification Using Adapted Gaussian Mixture Models (2000) — 5,008 citations
  8. HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units (2021) — 4,844 citations
  9. IEMOCAP: interactive emotional dyadic motion capture database (2008) — 4,482 citations
  10. Conformer: Convolution-augmented Transformer for Speech Recognition (2020) — 4,195 citations
  11. SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition (2019) — 4,125 citations
  12. Beyond the Kalman Filter: Particle Filters for Tracking Applications (2004) — 3,985 citations
  13. Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs (2001) — 3,796 citations
  14. Signal Processing (2013) — 3,700 citations
  15. Front-End Factor Analysis for Speaker Verification (2011) — 3,573 citations
  16. WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing (2021) — 3,371 citations
  17. Performance measurement in blind audio source separation (2006) — 3,197 citations
  18. Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions (2017) — 3,120 citations
  19. librosa: Audio and Music Signal Analysis in Python (2015) — 3,082 citations
  20. X-Vectors: Robust DNN Embeddings for Speaker Recognition (2018) — 3,060 citations
  21. VoxCeleb2: Deep Speaker Recognition (2018) — 2,807 citations
  22. Attention-Based Models for Speech Recognition (2015) — 2,769 citations
  23. VoxCeleb: A Large-Scale Speaker Identification Dataset (2017) — 2,732 citations
  24. Long short-term memory recurrent neural network architectures for large scale acoustic modeling (2014) — 2,571 citations
  25. Common Voice: A Massively-Multilingual Speech Corpus (2019) — 2,502 citations
  26. An Algorithm for Intelligibility Prediction of Time–Frequency Weighted Noisy Speech (2011) — 2,397 citations
  27. From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images (2009) — 2,385 citations
  28. YIN, a fundamental frequency estimator for speech and music. (2002) — 2,301 citations
  29. The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English (2018) — 2,268 citations
  30. Deep Speech: Scaling up end-to-end speech recognition (2014) — 2,263 citations
  31. Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation (2018) — 2,194 citations
  32. Convolutional Neural Networks for Speech Recognition (2014) — 2,165 citations
  33. The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions (2000) — 2,150 citations
  34. Tacotron: Towards End-to-End Speech Synthesis (2017) — 2,067 citations
  35. Using NLG for speech synthesis of mathematical sentences (2019) — 2,043 citations
  36. FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (2020) — 1,809 citations
  37. Fast Fourier Transform (2011) — 1,761 citations
  38. ESPnet: End-to-End Speech Processing Toolkit (2018) — 1,730 citations
  39. Front-End Factor Analysis For Speaker Verification (2018) — 1,716 citations
  40. MUSAN: A Music, Speech, and Noise Corpus (2015) — 1,702 citations
  41. SDR – Half-baked or Well Done? (2018) — 1,662 citations
  42. Statistical Parametric Speech Synthesis (2007) — 1,584 citations
  43. PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition (2019) — 1,568 citations
  44. A Dataset and Taxonomy for Urban Sound Research (2014) — 1,558 citations
  45. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi (2017) — 1,549 citations
  46. SoundStream: An End-to-End Neural Audio Codec (2021, IEEE/ACM Transactions on Audio Speech and Language Processing) — 1,407 citations
  47. AST: Audio Spectrogram Transformer (2021) — 1,388 citations
  48. LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech (2019) — 1,387 citations
  49. TIMIT Acoustic-Phonetic Continuous Speech Corpus (2012) — 1,364 citations
  50. A Regression Approach to Speech Enhancement Based on Deep Neural Networks (2015) — 1,344 citations

Most active researchers

By papers in this topic: a volume measure, not trust.