Josef V. Psutka

5 papers · 2017–2024 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (12)

Venues

Interspeech (5)

Top co-authors

Jan Švec (4) Luboš Šmídl (3) Aleš Pražák (2) Jan Lehečka (2) Pavel Ircing (2) Josef Psutka (2) Zdeněk Loose (1) Vlasta Radová (1) Jan Trmal (1)

Research topics

Deep Learning (4) Speech & Audio (4) Recognition (4) Architectures (3) Machine Learning (2) Core Methods (2) Learning Types · Machine Learning (2) Natural Language Processing (1) Applications (1) Learning Types · Deep Learning (1) Resources & Methods (1) Synthesis (1) Techniques (1)

Keywords

automatic speech recognition (3) pronunciation embedding (2) spoken term detection (2) siamese neural network (2) self-supervised learning (2) recurrent neural network (1) language model (1) siamese network (1) multilingual model (1) lstm network (1) cosine distance (1) wav2vec 2.0 (1) monolingual model (1) hearing impairment (1) multilingual speech recognition (1) transformer-based speech recognition (1) out-of-vocabulary term (1) live subtitling (1) oral history (1) transformer model (1)

Papers

A Comparative Analysis of Bilingual and Trilingual Wav2Vec Models for Automatic Speech Recognition in Multilingual Oral History Archives Interspeech 2024 Transformer-based Speech Recognition Models for Oral History Archives in English, German, and Czech Interspeech 2023 Live TV Subtitling Through Respeaking Interspeech 2021 Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings Interspeech 2021 A Relevance Score Estimation for Spoken Term Detection Based on RNN-Generated Pronunciation Embeddings Interspeech 2017