What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Speech recognition
Speech recognition, Artificial intelligence, Spoofing attack, Speaker recognition and Biometrics are his primary areas of study.
His Speech recognition research incorporates elements of Feature extraction and Mel-frequency cepstrum.
In his study, which falls under the umbrella issue of Artificial intelligence, Lossy compression is strongly linked to Pattern recognition.
His biological study spans a wide range of topics, including Isolation, Baseline and Speech synthesis.
His studies in Speaker recognition integrate themes in fields like Mixture model, Voice analysis and Natural language processing.
His research in Biometrics intersects with topics in Gaze and Eye movement.
His most cited work include:
- An overview of text-independent speaker recognition: From features to supervectors (1045 citations)
- Spoofing and countermeasures for speaker verification (280 citations)
- Real-time speaker identification and verification (213 citations)
What are the main themes of his work throughout his whole career to date?
Tomi Kinnunen focuses on Speech recognition, Artificial intelligence, Speaker recognition, Pattern recognition and Spoofing attack.
His Speech recognition study combines topics from a wide range of disciplines, such as Feature extraction and Mel-frequency cepstrum.
As part of the same scientific family, he usually focuses on Artificial intelligence, concentrating on Natural language processing and intersecting with I vector.
The various areas that Tomi Kinnunen examines in his Speaker recognition study include Context, Feature, Vocal effort, Utterance and Voice activity detection.
Tomi Kinnunen has researched Spoofing attack in several fields, including Replay attack, Speech synthesis and Biometrics.
His Mixture model research includes elements of Support vector machine and Vulnerability.
He most often published in these fields:
- Speech recognition (67.84%)
- Artificial intelligence (47.58%)
- Speaker recognition (40.53%)
What were the highlights of his more recent work (between 2017-2021)?
- Speech recognition (67.84%)
- Spoofing attack (28.19%)
- Speaker verification (25.11%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Speech recognition, Spoofing attack, Speaker verification, Artificial intelligence and Word error rate.
His study in Speech recognition is interdisciplinary in nature, drawing from both Feature extraction and Robustness.
His studies deal with areas such as Reliability, Replay attack, Speech synthesis and Biometrics as well as Spoofing attack.
His research integrates issues of Computer security, Formant and Constant false alarm rate in his study of Speaker verification.
His Artificial intelligence research is multidisciplinary, relying on both Machine learning, Audio signal and Pattern recognition.
His research investigates the link between Word error rate and topics such as Cepstrum that cross with problems in Artifact, Feature, Benchmark and Benchmarking.
Between 2017 and 2021, his most popular works were:
- The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods (125 citations)
- ASVspoof 2019: Future horizons in spoofed and fake audio detection (88 citations)
- t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification (68 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Speech recognition
Tomi Kinnunen mainly focuses on Spoofing attack, Speech recognition, Speaker verification, Word error rate and Speech synthesis.
His Spoofing attack research incorporates themes from Baseline, Replay attack and Reliability.
Speaker recognition is the focus of his Speech recognition research.
His work carried out in the field of Speaker recognition brings together such families of science as Linear prediction, Feature extraction, Mel-frequency cepstrum and Vocal tract.
His Word error rate research includes themes of Cepstrum, Benchmarking and Mixture model.
The study incorporates disciplines such as Speech enhancement and The Internet in addition to Speech synthesis.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
